[PATCH 4.4.y 001/101] x86/cpufeature: Move some of the scattered feature bits to x86_capability

[PATCH 4.4.y 001/101] x86/cpufeature: Move some of the scattered feature bits to x86_capability

[Srivatsa S. Bhat]

From: Borislav Petkov <bp@suse.de>

commit 2ccd71f1b278d450a6f8c8c737c7fe237ca06dc6 upstream

Turn the CPUID leafs which are proper CPUID feature bit leafs into
separate ->x86_capability words.

Signed-off-by: Borislav Petkov <bp@suse.de>
Link: http://lkml.kernel.org/r/1449481182-27541-2-git-send-email-bp@alien8.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeature.h |   54 ++++++++++++++++++++++---------------
 arch/x86/kernel/cpu/common.c      |    5 +++
 arch/x86/kernel/cpu/scattered.c   |   20 --------------
 3 files changed, 37 insertions(+), 42 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 232621c..999e166 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -12,7 +12,7 @@
 #include <asm/disabled-features.h>
 #endif
 
-#define NCAPINTS	14	/* N 32-bit words worth of info */
+#define NCAPINTS	16	/* N 32-bit words worth of info */
 #define NBUGINTS	1	/* N 32-bit bug flags */
 
 /*
@@ -181,23 +181,18 @@
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
- * CPUID levels like 0x6, 0xA etc, word 7
+ * CPUID levels like 0x6, 0xA etc, word 7.
+ *
+ * Reuse free bits when adding new feature flags!
  */
-#define X86_FEATURE_IDA		( 7*32+ 0) /* Intel Dynamic Acceleration */
-#define X86_FEATURE_ARAT	( 7*32+ 1) /* Always Running APIC Timer */
+
 #define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
 #define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
 #define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 4) /* Effectively INVPCID && CR4.PCIDE=1 */
-#define X86_FEATURE_PLN		( 7*32+ 5) /* Intel Power Limit Notification */
-#define X86_FEATURE_PTS		( 7*32+ 6) /* Intel Package Thermal Status */
-#define X86_FEATURE_DTHERM	( 7*32+ 7) /* Digital Thermal Sensor */
+
 #define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
-#define X86_FEATURE_HWP		( 7*32+ 10) /* "hwp" Intel HWP */
-#define X86_FEATURE_HWP_NOTIFY	( 7*32+ 11) /* Intel HWP_NOTIFY */
-#define X86_FEATURE_HWP_ACT_WINDOW ( 7*32+ 12) /* Intel HWP_ACT_WINDOW */
-#define X86_FEATURE_HWP_EPP	( 7*32+13) /* Intel HWP_EPP */
-#define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */
+
 #define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
 #define X86_FEATURE_RSB_CTXSW	( 7*32+19) /* Fill RSB on context switches */
 
@@ -212,16 +207,7 @@
 #define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */
 #define X86_FEATURE_EPT         ( 8*32+ 3) /* Intel Extended Page Table */
 #define X86_FEATURE_VPID        ( 8*32+ 4) /* Intel Virtual Processor ID */
-#define X86_FEATURE_NPT		( 8*32+ 5) /* AMD Nested Page Table support */
-#define X86_FEATURE_LBRV	( 8*32+ 6) /* AMD LBR Virtualization support */
-#define X86_FEATURE_SVML	( 8*32+ 7) /* "svm_lock" AMD SVM locking MSR */
-#define X86_FEATURE_NRIPS	( 8*32+ 8) /* "nrip_save" AMD SVM next_rip save */
-#define X86_FEATURE_TSCRATEMSR  ( 8*32+ 9) /* "tsc_scale" AMD TSC scaling support */
-#define X86_FEATURE_VMCBCLEAN   ( 8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */
-#define X86_FEATURE_FLUSHBYASID ( 8*32+11) /* AMD flush-by-ASID support */
-#define X86_FEATURE_DECODEASSISTS ( 8*32+12) /* AMD Decode Assists support */
-#define X86_FEATURE_PAUSEFILTER ( 8*32+13) /* AMD filtered pause intercept */
-#define X86_FEATURE_PFTHRESHOLD ( 8*32+14) /* AMD pause filter threshold */
+
 #define X86_FEATURE_VMMCALL     ( 8*32+15) /* Prefer vmmcall to vmcall */
 #define X86_FEATURE_XENPV       ( 8*32+16) /* "" Xen paravirtual guest */
 
@@ -266,6 +252,30 @@
 /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
 #define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
 
+/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
+#define X86_FEATURE_DTHERM	(14*32+ 0) /* Digital Thermal Sensor */
+#define X86_FEATURE_IDA		(14*32+ 1) /* Intel Dynamic Acceleration */
+#define X86_FEATURE_ARAT	(14*32+ 2) /* Always Running APIC Timer */
+#define X86_FEATURE_PLN		(14*32+ 4) /* Intel Power Limit Notification */
+#define X86_FEATURE_PTS		(14*32+ 6) /* Intel Package Thermal Status */
+#define X86_FEATURE_HWP		(14*32+ 7) /* Intel Hardware P-states */
+#define X86_FEATURE_HWP_NOTIFY	(14*32+ 8) /* HWP Notification */
+#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */
+#define X86_FEATURE_HWP_EPP	(14*32+10) /* HWP Energy Perf. Preference */
+#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */
+
+/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */
+#define X86_FEATURE_NPT		(15*32+ 0) /* Nested Page Table support */
+#define X86_FEATURE_LBRV	(15*32+ 1) /* LBR Virtualization support */
+#define X86_FEATURE_SVML	(15*32+ 2) /* "svm_lock" SVM locking MSR */
+#define X86_FEATURE_NRIPS	(15*32+ 3) /* "nrip_save" SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR  (15*32+ 4) /* "tsc_scale" TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN   (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
+
 /*
  * BUG word(s)
  */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 0498ad3..2007dfc 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -695,6 +695,8 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx);
 
 		c->x86_capability[9] = ebx;
+
+		c->x86_capability[14] = cpuid_eax(0x00000006);
 	}
 
 	/* Extended state features: level 0x0000000d */
@@ -756,6 +758,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 	if (c->extended_cpuid_level >= 0x80000007)
 		c->x86_power = cpuid_edx(0x80000007);
 
+	if (c->extended_cpuid_level >= 0x8000000a)
+		c->x86_capability[15] = cpuid_edx(0x8000000a);
+
 	init_scattered_cpuid_features(c);
 }
 
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 608fb26..8cb57df 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -31,32 +31,12 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 	const struct cpuid_bit *cb;
 
 	static const struct cpuid_bit cpuid_bits[] = {
-		{ X86_FEATURE_DTHERM,		CR_EAX, 0, 0x00000006, 0 },
-		{ X86_FEATURE_IDA,		CR_EAX, 1, 0x00000006, 0 },
-		{ X86_FEATURE_ARAT,		CR_EAX, 2, 0x00000006, 0 },
-		{ X86_FEATURE_PLN,		CR_EAX, 4, 0x00000006, 0 },
-		{ X86_FEATURE_PTS,		CR_EAX, 6, 0x00000006, 0 },
-		{ X86_FEATURE_HWP,		CR_EAX, 7, 0x00000006, 0 },
-		{ X86_FEATURE_HWP_NOTIFY,	CR_EAX, 8, 0x00000006, 0 },
-		{ X86_FEATURE_HWP_ACT_WINDOW,	CR_EAX, 9, 0x00000006, 0 },
-		{ X86_FEATURE_HWP_EPP,		CR_EAX,10, 0x00000006, 0 },
-		{ X86_FEATURE_HWP_PKG_REQ,	CR_EAX,11, 0x00000006, 0 },
 		{ X86_FEATURE_INTEL_PT,		CR_EBX,25, 0x00000007, 0 },
 		{ X86_FEATURE_APERFMPERF,	CR_ECX, 0, 0x00000006, 0 },
 		{ X86_FEATURE_EPB,		CR_ECX, 3, 0x00000006, 0 },
 		{ X86_FEATURE_HW_PSTATE,	CR_EDX, 7, 0x80000007, 0 },
 		{ X86_FEATURE_CPB,		CR_EDX, 9, 0x80000007, 0 },
 		{ X86_FEATURE_PROC_FEEDBACK,	CR_EDX,11, 0x80000007, 0 },
-		{ X86_FEATURE_NPT,		CR_EDX, 0, 0x8000000a, 0 },
-		{ X86_FEATURE_LBRV,		CR_EDX, 1, 0x8000000a, 0 },
-		{ X86_FEATURE_SVML,		CR_EDX, 2, 0x8000000a, 0 },
-		{ X86_FEATURE_NRIPS,		CR_EDX, 3, 0x8000000a, 0 },
-		{ X86_FEATURE_TSCRATEMSR,	CR_EDX, 4, 0x8000000a, 0 },
-		{ X86_FEATURE_VMCBCLEAN,	CR_EDX, 5, 0x8000000a, 0 },
-		{ X86_FEATURE_FLUSHBYASID,	CR_EDX, 6, 0x8000000a, 0 },
-		{ X86_FEATURE_DECODEASSISTS,	CR_EDX, 7, 0x8000000a, 0 },
-		{ X86_FEATURE_PAUSEFILTER,	CR_EDX,10, 0x8000000a, 0 },
-		{ X86_FEATURE_PFTHRESHOLD,	CR_EDX,12, 0x8000000a, 0 },
 		{ 0, 0, 0, 0, 0 }
 	};
 

[PATCH 4.4.y 002/101] x86/cpufeature: Cleanup get_cpu_cap()

[Srivatsa S. Bhat]

From: Borislav Petkov <bp@suse.de>

commit 39c06df4dc10a41de5fe706f4378ee5f09beba73 upstream

Add an enum for the ->x86_capability array indices and cleanup
get_cpu_cap() by killing some redundant local vars.

Signed-off-by: Borislav Petkov <bp@suse.de>
Link: http://lkml.kernel.org/r/1449481182-27541-3-git-send-email-bp@alien8.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeature.h |   20 ++++++++++++++++
 arch/x86/kernel/cpu/centaur.c     |    2 +-
 arch/x86/kernel/cpu/common.c      |   47 +++++++++++++++++--------------------
 arch/x86/kernel/cpu/transmeta.c   |    4 ++-
 4 files changed, 45 insertions(+), 28 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 999e166..54c7a0b 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -299,6 +299,26 @@
 #include <asm/asm.h>
 #include <linux/bitops.h>
 
+enum cpuid_leafs
+{
+	CPUID_1_EDX		= 0,
+	CPUID_8000_0001_EDX,
+	CPUID_8086_0001_EDX,
+	CPUID_LNX_1,
+	CPUID_1_ECX,
+	CPUID_C000_0001_EDX,
+	CPUID_8000_0001_ECX,
+	CPUID_LNX_2,
+	CPUID_LNX_3,
+	CPUID_7_0_EBX,
+	CPUID_D_1_EAX,
+	CPUID_F_0_EDX,
+	CPUID_F_1_EDX,
+	CPUID_8000_0008_EBX,
+	CPUID_6_EAX,
+	CPUID_8000_000A_EDX,
+};
+
 #ifdef CONFIG_X86_FEATURE_NAMES
 extern const char * const x86_cap_flags[NCAPINTS*32];
 extern const char * const x86_power_flags[32];
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index d8fba5c..ae20be6 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -43,7 +43,7 @@ static void init_c3(struct cpuinfo_x86 *c)
 		/* store Centaur Extended Feature Flags as
 		 * word 5 of the CPU capability bit array
 		 */
-		c->x86_capability[5] = cpuid_edx(0xC0000001);
+		c->x86_capability[CPUID_C000_0001_EDX] = cpuid_edx(0xC0000001);
 	}
 #ifdef CONFIG_X86_32
 	/* Cyrix III family needs CX8 & PGE explicitly enabled. */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 2007dfc..5b6e43b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -676,52 +676,47 @@ static void apply_forced_caps(struct cpuinfo_x86 *c)
 
 void get_cpu_cap(struct cpuinfo_x86 *c)
 {
-	u32 tfms, xlvl;
-	u32 ebx;
+	u32 eax, ebx, ecx, edx;
 
 	/* Intel-defined flags: level 0x00000001 */
 	if (c->cpuid_level >= 0x00000001) {
-		u32 capability, excap;
+		cpuid(0x00000001, &eax, &ebx, &ecx, &edx);
 
-		cpuid(0x00000001, &tfms, &ebx, &excap, &capability);
-		c->x86_capability[0] = capability;
-		c->x86_capability[4] = excap;
+		c->x86_capability[CPUID_1_ECX] = ecx;
+		c->x86_capability[CPUID_1_EDX] = edx;
 	}
 
 	/* Additional Intel-defined flags: level 0x00000007 */
 	if (c->cpuid_level >= 0x00000007) {
-		u32 eax, ebx, ecx, edx;
-
 		cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx);
 
-		c->x86_capability[9] = ebx;
+		c->x86_capability[CPUID_7_0_EBX] = ebx;
 
-		c->x86_capability[14] = cpuid_eax(0x00000006);
+		c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006);
 	}
 
 	/* Extended state features: level 0x0000000d */
 	if (c->cpuid_level >= 0x0000000d) {
-		u32 eax, ebx, ecx, edx;
-
 		cpuid_count(0x0000000d, 1, &eax, &ebx, &ecx, &edx);
 
-		c->x86_capability[10] = eax;
+		c->x86_capability[CPUID_D_1_EAX] = eax;
 	}
 
 	/* Additional Intel-defined flags: level 0x0000000F */
 	if (c->cpuid_level >= 0x0000000F) {
-		u32 eax, ebx, ecx, edx;
 
 		/* QoS sub-leaf, EAX=0Fh, ECX=0 */
 		cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx);
-		c->x86_capability[11] = edx;
+		c->x86_capability[CPUID_F_0_EDX] = edx;
+
 		if (cpu_has(c, X86_FEATURE_CQM_LLC)) {
 			/* will be overridden if occupancy monitoring exists */
 			c->x86_cache_max_rmid = ebx;
 
 			/* QoS sub-leaf, EAX=0Fh, ECX=1 */
 			cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx);
-			c->x86_capability[12] = edx;
+			c->x86_capability[CPUID_F_1_EDX] = edx;
+
 			if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) {
 				c->x86_cache_max_rmid = ecx;
 				c->x86_cache_occ_scale = ebx;
@@ -733,22 +728,24 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 	}
 
 	/* AMD-defined flags: level 0x80000001 */
-	xlvl = cpuid_eax(0x80000000);
-	c->extended_cpuid_level = xlvl;
+	eax = cpuid_eax(0x80000000);
+	c->extended_cpuid_level = eax;
+
+	if ((eax & 0xffff0000) == 0x80000000) {
+		if (eax >= 0x80000001) {
+			cpuid(0x80000001, &eax, &ebx, &ecx, &edx);
 
-	if ((xlvl & 0xffff0000) == 0x80000000) {
-		if (xlvl >= 0x80000001) {
-			c->x86_capability[1] = cpuid_edx(0x80000001);
-			c->x86_capability[6] = cpuid_ecx(0x80000001);
+			c->x86_capability[CPUID_8000_0001_ECX] = ecx;
+			c->x86_capability[CPUID_8000_0001_EDX] = edx;
 		}
 	}
 
 	if (c->extended_cpuid_level >= 0x80000008) {
-		u32 eax = cpuid_eax(0x80000008);
+		cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
 
 		c->x86_virt_bits = (eax >> 8) & 0xff;
 		c->x86_phys_bits = eax & 0xff;
-		c->x86_capability[13] = cpuid_ebx(0x80000008);
+		c->x86_capability[CPUID_8000_0008_EBX] = ebx;
 	}
 #ifdef CONFIG_X86_32
 	else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
@@ -759,7 +756,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_power = cpuid_edx(0x80000007);
 
 	if (c->extended_cpuid_level >= 0x8000000a)
-		c->x86_capability[15] = cpuid_edx(0x8000000a);
+		c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
 
 	init_scattered_cpuid_features(c);
 }
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index 3fa0e5a..252da7a 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -12,7 +12,7 @@ static void early_init_transmeta(struct cpuinfo_x86 *c)
 	xlvl = cpuid_eax(0x80860000);
 	if ((xlvl & 0xffff0000) == 0x80860000) {
 		if (xlvl >= 0x80860001)
-			c->x86_capability[2] = cpuid_edx(0x80860001);
+			c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001);
 	}
 }
 
@@ -82,7 +82,7 @@ static void init_transmeta(struct cpuinfo_x86 *c)
 	/* Unhide possibly hidden capability flags */
 	rdmsr(0x80860004, cap_mask, uk);
 	wrmsr(0x80860004, ~0, uk);
-	c->x86_capability[0] = cpuid_edx(0x00000001);
+	c->x86_capability[CPUID_1_EDX] = cpuid_edx(0x00000001);
 	wrmsr(0x80860004, cap_mask, uk);
 
 	/* All Transmeta CPUs have a constant TSC */

[PATCH 4.4.y 003/101] x86/cpu: Provide a config option to disable static_cpu_has

[Srivatsa S. Bhat]

From: Borislav Petkov <bp@suse.de>

commit 6e1315fe82308cd29e7550eab967262e8bbc71a3 upstream

This brings .text savings of about ~1.6K when building a tinyconfig. It
is off by default so nothing changes for the default.

Kconfig help text from Josh.

Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Link: http://lkml.kernel.org/r/1449481182-27541-5-git-send-email-bp@alien8.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/Kconfig                  |   11 +++++++++++
 arch/x86/include/asm/cpufeature.h |    2 +-
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index eab1ef2..d9afe6d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -346,6 +346,17 @@ config X86_FEATURE_NAMES
 
 	  If in doubt, say Y.
 
+config X86_FAST_FEATURE_TESTS
+	bool "Fast CPU feature tests" if EMBEDDED
+	default y
+	---help---
+	  Some fast-paths in the kernel depend on the capabilities of the CPU.
+	  Say Y here for the kernel to patch in the appropriate code at runtime
+	  based on the capabilities of the CPU. The infrastructure for patching
+	  code at runtime takes up some additional space; space-constrained
+	  embedded systems may wish to say N here to produce smaller, slightly
+	  slower code.
+
 config X86_X2APIC
 	bool "Support x2apic"
 	depends on X86_LOCAL_APIC && X86_64 && (IRQ_REMAP || HYPERVISOR_GUEST)
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 54c7a0b..67f917b 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -422,7 +422,7 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
  * fast paths and boot_cpu_has() otherwise!
  */
 
-#if __GNUC__ >= 4
+#if __GNUC__ >= 4 && defined(CONFIG_X86_FAST_FEATURE_TESTS)
 extern void warn_pre_alternatives(void);
 extern bool __static_cpu_has_safe(u16 bit);
 

[PATCH 4.4.y 004/101] x86/fpu: Add an XSTATE_OP() macro

[Srivatsa S. Bhat]

From: Borislav Petkov <bp@suse.de>

commit b74a0cf1b3db30173eefa00c411775d2b1697700 upstream

Add an XSTATE_OP() macro which contains the XSAVE* fault handling
and replace all non-alternatives users of xstate_fault() with
it.

This fixes also the buglet in copy_xregs_to_user() and
copy_user_to_xregs() where the inline asm didn't have @xstate as
memory reference and thus potentially causing unwanted
reordering of accesses to the extended state.

Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1447932326-4371-2-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/fpu/internal.h |   68 ++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 37 deletions(-)

diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 146d838..839e7b6 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -238,6 +238,20 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu)
 	_ASM_EXTABLE(1b, 3b)		\
 	: [_err] "=r" (__err)
 
+#define XSTATE_OP(op, st, lmask, hmask, err)				\
+	asm volatile("1:" op "\n\t"					\
+		     "xor %[err], %[err]\n"				\
+		     "2:\n\t"						\
+		     ".pushsection .fixup,\"ax\"\n\t"			\
+		     "3: movl $-2,%[err]\n\t"				\
+		     "jmp 2b\n\t"					\
+		     ".popsection\n\t"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : [err] "=r" (err)					\
+		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : "memory")
+
+
 /*
  * This function is called only during boot time when x86 caps are not set
  * up and alternative can not be used yet.
@@ -247,22 +261,14 @@ static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate)
 	u64 mask = -1;
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
-	int err = 0;
+	int err;
 
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		asm volatile("1:"XSAVES"\n\t"
-			"2:\n\t"
-			     xstate_fault(err)
-			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
-			: "memory");
+	if (static_cpu_has_safe(X86_FEATURE_XSAVES))
+		XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
 	else
-		asm volatile("1:"XSAVE"\n\t"
-			"2:\n\t"
-			     xstate_fault(err)
-			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
-			: "memory");
+		XSTATE_OP(XSAVE, xstate, lmask, hmask, err);
 
 	/* We should never fault when copying to a kernel buffer: */
 	WARN_ON_FPU(err);
@@ -277,22 +283,14 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
 	u64 mask = -1;
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
-	int err = 0;
+	int err;
 
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		asm volatile("1:"XRSTORS"\n\t"
-			"2:\n\t"
-			     xstate_fault(err)
-			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
-			: "memory");
+	if (static_cpu_has_safe(X86_FEATURE_XSAVES))
+		XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
 	else
-		asm volatile("1:"XRSTOR"\n\t"
-			"2:\n\t"
-			     xstate_fault(err)
-			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
-			: "memory");
+		XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
 
 	/* We should never fault when copying from a kernel buffer: */
 	WARN_ON_FPU(err);
@@ -389,12 +387,10 @@ static inline int copy_xregs_to_user(struct xregs_state __user *buf)
 	if (unlikely(err))
 		return -EFAULT;
 
-	__asm__ __volatile__(ASM_STAC "\n"
-			     "1:"XSAVE"\n"
-			     "2: " ASM_CLAC "\n"
-			     xstate_fault(err)
-			     : "D" (buf), "a" (-1), "d" (-1), "0" (err)
-			     : "memory");
+	stac();
+	XSTATE_OP(XSAVE, buf, -1, -1, err);
+	clac();
+
 	return err;
 }
 
@@ -406,14 +402,12 @@ static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask)
 	struct xregs_state *xstate = ((__force struct xregs_state *)buf);
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
-	int err = 0;
+	int err;
+
+	stac();
+	XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
+	clac();
 
-	__asm__ __volatile__(ASM_STAC "\n"
-			     "1:"XRSTOR"\n"
-			     "2: " ASM_CLAC "\n"
-			     xstate_fault(err)
-			     : "D" (xstate), "a" (lmask), "d" (hmask), "0" (err)
-			     : "memory");	/* memory required? */
 	return err;
 }
 

[PATCH 4.4.y 005/101] x86/fpu: Get rid of xstate_fault()

[Srivatsa S. Bhat]

From: Borislav Petkov <bp@suse.de>

commit b7106fa0f29f9fd83d2d1905ab690d334ef855c1 upstream

Add macros for the alternative XSAVE*/XRSTOR* operations which
contain the fault handling and use them. Kill xstate_fault().

Also, copy_xregs_to_kernel() didn't have the extended state as
memory reference in the asm.

Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1447932326-4371-3-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/fpu/internal.h |  105 +++++++++++++++++------------------
 1 file changed, 52 insertions(+), 53 deletions(-)

diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 839e7b6..60c984a 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -225,19 +225,6 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu)
 #define XRSTOR		".byte " REX_PREFIX "0x0f,0xae,0x2f"
 #define XRSTORS		".byte " REX_PREFIX "0x0f,0xc7,0x1f"
 
-/* xstate instruction fault handler: */
-#define xstate_fault(__err)		\
-					\
-	".section .fixup,\"ax\"\n"	\
-					\
-	"3:  movl $-2,%[_err]\n"	\
-	"    jmp  2b\n"			\
-					\
-	".previous\n"			\
-					\
-	_ASM_EXTABLE(1b, 3b)		\
-	: [_err] "=r" (__err)
-
 #define XSTATE_OP(op, st, lmask, hmask, err)				\
 	asm volatile("1:" op "\n\t"					\
 		     "xor %[err], %[err]\n"				\
@@ -251,6 +238,54 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu)
 		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
 		     : "memory")
 
+/*
+ * If XSAVES is enabled, it replaces XSAVEOPT because it supports a compact
+ * format and supervisor states in addition to modified optimization in
+ * XSAVEOPT.
+ *
+ * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT
+ * supports modified optimization which is not supported by XSAVE.
+ *
+ * We use XSAVE as a fallback.
+ *
+ * The 661 label is defined in the ALTERNATIVE* macros as the address of the
+ * original instruction which gets replaced. We need to use it here as the
+ * address of the instruction where we might get an exception at.
+ */
+#define XSTATE_XSAVE(st, lmask, hmask, err)				\
+	asm volatile(ALTERNATIVE_2(XSAVE,				\
+				   XSAVEOPT, X86_FEATURE_XSAVEOPT,	\
+				   XSAVES,   X86_FEATURE_XSAVES)	\
+		     "\n"						\
+		     "xor %[err], %[err]\n"				\
+		     "3:\n"						\
+		     ".pushsection .fixup,\"ax\"\n"			\
+		     "4: movl $-2, %[err]\n"				\
+		     "jmp 3b\n"						\
+		     ".popsection\n"					\
+		     _ASM_EXTABLE(661b, 4b)				\
+		     : [err] "=r" (err)					\
+		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : "memory")
+
+/*
+ * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact
+ * XSAVE area format.
+ */
+#define XSTATE_XRESTORE(st, lmask, hmask, err)				\
+	asm volatile(ALTERNATIVE(XRSTOR,				\
+				 XRSTORS, X86_FEATURE_XSAVES)		\
+		     "\n"						\
+		     "xor %[err], %[err]\n"				\
+		     "3:\n"						\
+		     ".pushsection .fixup,\"ax\"\n"			\
+		     "4: movl $-2, %[err]\n"				\
+		     "jmp 3b\n"						\
+		     ".popsection\n"					\
+		     _ASM_EXTABLE(661b, 4b)				\
+		     : [err] "=r" (err)					\
+		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : "memory")
 
 /*
  * This function is called only during boot time when x86 caps are not set
@@ -304,33 +339,11 @@ static inline void copy_xregs_to_kernel(struct xregs_state *xstate)
 	u64 mask = -1;
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
-	int err = 0;
+	int err;
 
 	WARN_ON(!alternatives_patched);
 
-	/*
-	 * If xsaves is enabled, xsaves replaces xsaveopt because
-	 * it supports compact format and supervisor states in addition to
-	 * modified optimization in xsaveopt.
-	 *
-	 * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave
-	 * because xsaveopt supports modified optimization which is not
-	 * supported by xsave.
-	 *
-	 * If none of xsaves and xsaveopt is enabled, use xsave.
-	 */
-	alternative_input_2(
-		"1:"XSAVE,
-		XSAVEOPT,
-		X86_FEATURE_XSAVEOPT,
-		XSAVES,
-		X86_FEATURE_XSAVES,
-		[xstate] "D" (xstate), "a" (lmask), "d" (hmask) :
-		"memory");
-	asm volatile("2:\n\t"
-		     xstate_fault(err)
-		     : "0" (err)
-		     : "memory");
+	XSTATE_XSAVE(xstate, lmask, hmask, err);
 
 	/* We should never fault when copying to a kernel buffer: */
 	WARN_ON_FPU(err);
@@ -343,23 +356,9 @@ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask)
 {
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
-	int err = 0;
+	int err;
 
-	/*
-	 * Use xrstors to restore context if it is enabled. xrstors supports
-	 * compacted format of xsave area which is not supported by xrstor.
-	 */
-	alternative_input(
-		"1: " XRSTOR,
-		XRSTORS,
-		X86_FEATURE_XSAVES,
-		"D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask)
-		: "memory");
-
-	asm volatile("2:\n"
-		     xstate_fault(err)
-		     : "0" (err)
-		     : "memory");
+	XSTATE_XRESTORE(xstate, lmask, hmask, err);
 
 	/* We should never fault when copying from a kernel buffer: */
 	WARN_ON_FPU(err);

[PATCH 4.4.y 006/101] x86/headers: Don't include asm/processor.h in asm/atomic.h

[Srivatsa S. Bhat]

From: Andi Kleen <ak@linux.intel.com>

commit 153a4334c439cfb62e1d31cee0c790ba4157813d upstream

asm/atomic.h doesn't really need asm/processor.h anymore. Everything
it uses has moved to other header files. So remove that include.

processor.h is a nasty header that includes lots of
other headers and makes it prone to include loops. Removing the
include here makes asm/atomic.h a "leaf" header that can
be safely included in most other headers.

The only fallout is in the lib/atomic tester which relied on
this implicit include. Give it an explicit include.
(the include is in ifdef because the user is also in ifdef)

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: rostedt@goodmis.org
Link: http://lkml.kernel.org/r/1449018060-1742-1-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/atomic.h      |    1 -
 arch/x86/include/asm/atomic64_32.h |    1 -
 lib/atomic64_test.c                |    4 ++++
 3 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index ae5fb83..3e86742 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -3,7 +3,6 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include <asm/processor.h>
 #include <asm/alternative.h>
 #include <asm/cmpxchg.h>
 #include <asm/rmwcc.h>
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index a11c30b..a984111 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -3,7 +3,6 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include <asm/processor.h>
 //#include <asm/cmpxchg.h>
 
 /* An 64bit atomic type */
diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c
index 83c33a5b..d51e25a 100644
--- a/lib/atomic64_test.c
+++ b/lib/atomic64_test.c
@@ -16,6 +16,10 @@
 #include <linux/kernel.h>
 #include <linux/atomic.h>
 
+#ifdef CONFIG_X86
+#include <asm/processor.h>	/* for boot_cpu_has below */
+#endif
+
 #define TEST(bit, op, c_op, val)				\
 do {								\
 	atomic##bit##_set(&v, v0);				\

[PATCH 4.4.y 007/101] x86/cpufeature: Carve out X86_FEATURE_*

[Srivatsa S. Bhat]

From: Borislav Petkov <bp@suse.de>

commit cd4d09ec6f6c12a2cc3db5b7d8876a325a53545b upstream

Move them to a separate header and have the following
dependency:

  x86/cpufeatures.h <- x86/processor.h <- x86/cpufeature.h

This makes it easier to use the header in asm code and not
include the whole cpufeature.h and add guards for asm.

Suggested-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1453842730-28463-5-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 Documentation/kernel-parameters.txt      |    2 
 arch/x86/boot/cpuflags.h                 |    2 
 arch/x86/boot/mkcpustr.c                 |    2 
 arch/x86/crypto/crc32-pclmul_glue.c      |    2 
 arch/x86/crypto/crc32c-intel_glue.c      |    2 
 arch/x86/crypto/crct10dif-pclmul_glue.c  |    2 
 arch/x86/entry/common.c                  |    1 
 arch/x86/entry/entry_32.S                |    2 
 arch/x86/entry/vdso/vdso32-setup.c       |    1 
 arch/x86/entry/vdso/vdso32/system_call.S |    2 
 arch/x86/entry/vdso/vma.c                |    1 
 arch/x86/include/asm/alternative.h       |    6 -
 arch/x86/include/asm/apic.h              |    1 
 arch/x86/include/asm/arch_hweight.h      |    2 
 arch/x86/include/asm/cmpxchg.h           |    1 
 arch/x86/include/asm/cpufeature.h        |  293 ------------------------------
 arch/x86/include/asm/cpufeatures.h       |  297 ++++++++++++++++++++++++++++++
 arch/x86/include/asm/fpu/internal.h      |    1 
 arch/x86/include/asm/irq_work.h          |    2 
 arch/x86/include/asm/mwait.h             |    2 
 arch/x86/include/asm/nospec-branch.h     |    2 
 arch/x86/include/asm/processor.h         |    3 
 arch/x86/include/asm/smap.h              |    2 
 arch/x86/include/asm/smp.h               |    1 
 arch/x86/include/asm/thread_info.h       |    2 
 arch/x86/include/asm/tlbflush.h          |    1 
 arch/x86/include/asm/uaccess_64.h        |    2 
 arch/x86/kernel/cpu/Makefile             |    2 
 arch/x86/kernel/cpu/centaur.c            |    2 
 arch/x86/kernel/cpu/cyrix.c              |    1 
 arch/x86/kernel/cpu/intel.c              |    2 
 arch/x86/kernel/cpu/intel_cacheinfo.c    |    2 
 arch/x86/kernel/cpu/match.c              |    2 
 arch/x86/kernel/cpu/mkcapflags.sh        |    6 -
 arch/x86/kernel/cpu/mtrr/main.c          |    2 
 arch/x86/kernel/cpu/transmeta.c          |    2 
 arch/x86/kernel/e820.c                   |    1 
 arch/x86/kernel/head_32.S                |    2 
 arch/x86/kernel/hpet.c                   |    1 
 arch/x86/kernel/msr.c                    |    2 
 arch/x86/kernel/verify_cpu.S             |    2 
 arch/x86/lib/clear_page_64.S             |    2 
 arch/x86/lib/copy_page_64.S              |    2 
 arch/x86/lib/copy_user_64.S              |    2 
 arch/x86/lib/memcpy_64.S                 |    2 
 arch/x86/lib/memmove_64.S                |    2 
 arch/x86/lib/memset_64.S                 |    2 
 arch/x86/lib/retpoline.S                 |    2 
 arch/x86/mm/setup_nx.c                   |    1 
 arch/x86/oprofile/op_model_amd.c         |    1 
 arch/x86/um/asm/barrier.h                |    2 
 lib/atomic64_test.c                      |    2 
 52 files changed, 347 insertions(+), 339 deletions(-)
 create mode 100644 arch/x86/include/asm/cpufeatures.h

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 4df6bd7..e60d0b5 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -652,7 +652,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	clearcpuid=BITNUM [X86]
 			Disable CPUID feature X for the kernel. See
-			arch/x86/include/asm/cpufeature.h for the valid bit
+			arch/x86/include/asm/cpufeatures.h for the valid bit
 			numbers. Note the Linux specific bits are not necessarily
 			stable over kernel options, but the vendor specific
 			ones should be.
diff --git a/arch/x86/boot/cpuflags.h b/arch/x86/boot/cpuflags.h
index ea97697..4cb404f 100644
--- a/arch/x86/boot/cpuflags.h
+++ b/arch/x86/boot/cpuflags.h
@@ -1,7 +1,7 @@
 #ifndef BOOT_CPUFLAGS_H
 #define BOOT_CPUFLAGS_H
 
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/processor-flags.h>
 
 struct cpu_features {
diff --git a/arch/x86/boot/mkcpustr.c b/arch/x86/boot/mkcpustr.c
index 637097e..f72498d 100644
--- a/arch/x86/boot/mkcpustr.c
+++ b/arch/x86/boot/mkcpustr.c
@@ -17,7 +17,7 @@
 
 #include "../include/asm/required-features.h"
 #include "../include/asm/disabled-features.h"
-#include "../include/asm/cpufeature.h"
+#include "../include/asm/cpufeatures.h"
 #include "../kernel/cpu/capflags.c"
 
 int main(void)
diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c
index 07d2c6c..27226df 100644
--- a/arch/x86/crypto/crc32-pclmul_glue.c
+++ b/arch/x86/crypto/crc32-pclmul_glue.c
@@ -33,7 +33,7 @@
 #include <linux/crc32.h>
 #include <crypto/internal/hash.h>
 
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/cpu_device_id.h>
 #include <asm/fpu/api.h>
 
diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index 15f5c76..715399b 100644
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -30,7 +30,7 @@
 #include <linux/kernel.h>
 #include <crypto/internal/hash.h>
 
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/cpu_device_id.h>
 #include <asm/fpu/internal.h>
 
diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c
index a3fcfc9..cd4df93 100644
--- a/arch/x86/crypto/crct10dif-pclmul_glue.c
+++ b/arch/x86/crypto/crct10dif-pclmul_glue.c
@@ -30,7 +30,7 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <asm/fpu/api.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/cpu_device_id.h>
 
 asmlinkage __u16 crc_t10dif_pcl(__u16 crc, const unsigned char *buf,
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index b5eb1cc..071582a 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -27,6 +27,7 @@
 #include <asm/traps.h>
 #include <asm/vdso.h>
 #include <asm/uaccess.h>
+#include <asm/cpufeature.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index d437f387..49a8c9f 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -40,7 +40,7 @@
 #include <asm/processor-flags.h>
 #include <asm/ftrace.h>
 #include <asm/irq_vectors.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index a7508d7..3f9d1a8 100644
--- a/arch/x86/entry/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
@@ -11,7 +11,6 @@
 #include <linux/kernel.h>
 #include <linux/mm_types.h>
 
-#include <asm/cpufeature.h>
 #include <asm/processor.h>
 #include <asm/vdso.h>
 
diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S
index 3a1d929..0109ac6 100644
--- a/arch/x86/entry/vdso/vdso32/system_call.S
+++ b/arch/x86/entry/vdso/vdso32/system_call.S
@@ -3,7 +3,7 @@
 */
 
 #include <asm/dwarf2.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 /*
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index b8f69e2..5471ac3 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -20,6 +20,7 @@
 #include <asm/page.h>
 #include <asm/hpet.h>
 #include <asm/desc.h>
+#include <asm/cpufeature.h>
 
 #if defined(CONFIG_X86_64)
 unsigned int __read_mostly vdso64_enabled = 1;
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 215ea92..002fcd9 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -154,12 +154,6 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	".popsection\n"
 
 /*
- * This must be included *after* the definition of ALTERNATIVE due to
- * <asm/arch_hweight.h>
- */
-#include <asm/cpufeature.h>
-
-/*
  * Alternative instructions for different CPU types or capabilities.
  *
  * This allows to use optimized instructions even on generic binary
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 163769d..fd810a5 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -6,7 +6,6 @@
 
 #include <asm/alternative.h>
 #include <asm/cpufeature.h>
-#include <asm/processor.h>
 #include <asm/apicdef.h>
 #include <linux/atomic.h>
 #include <asm/fixmap.h>
diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h
index 44f825c..e7cd631 100644
--- a/arch/x86/include/asm/arch_hweight.h
+++ b/arch/x86/include/asm/arch_hweight.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_HWEIGHT_H
 #define _ASM_X86_HWEIGHT_H
 
+#include <asm/cpufeatures.h>
+
 #ifdef CONFIG_64BIT
 /* popcnt %edi, %eax */
 #define POPCNT32 ".byte 0xf3,0x0f,0xb8,0xc7"
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index ad19841..9733361 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -2,6 +2,7 @@
 #define ASM_X86_CMPXCHG_H
 
 #include <linux/compiler.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative.h> /* Provides LOCK_PREFIX */
 
 /*
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 67f917b..f62e872 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -1,298 +1,7 @@
-/*
- * Defines x86 CPU feature bits
- */
 #ifndef _ASM_X86_CPUFEATURE_H
 #define _ASM_X86_CPUFEATURE_H
 
-#ifndef _ASM_X86_REQUIRED_FEATURES_H
-#include <asm/required-features.h>
-#endif
-
-#ifndef _ASM_X86_DISABLED_FEATURES_H
-#include <asm/disabled-features.h>
-#endif
-
-#define NCAPINTS	16	/* N 32-bit words worth of info */
-#define NBUGINTS	1	/* N 32-bit bug flags */
-
-/*
- * Note: If the comment begins with a quoted string, that string is used
- * in /proc/cpuinfo instead of the macro name.  If the string is "",
- * this feature bit is not displayed in /proc/cpuinfo at all.
- */
-
-/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
-#define X86_FEATURE_FPU		( 0*32+ 0) /* Onboard FPU */
-#define X86_FEATURE_VME		( 0*32+ 1) /* Virtual Mode Extensions */
-#define X86_FEATURE_DE		( 0*32+ 2) /* Debugging Extensions */
-#define X86_FEATURE_PSE		( 0*32+ 3) /* Page Size Extensions */
-#define X86_FEATURE_TSC		( 0*32+ 4) /* Time Stamp Counter */
-#define X86_FEATURE_MSR		( 0*32+ 5) /* Model-Specific Registers */
-#define X86_FEATURE_PAE		( 0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE		( 0*32+ 7) /* Machine Check Exception */
-#define X86_FEATURE_CX8		( 0*32+ 8) /* CMPXCHG8 instruction */
-#define X86_FEATURE_APIC	( 0*32+ 9) /* Onboard APIC */
-#define X86_FEATURE_SEP		( 0*32+11) /* SYSENTER/SYSEXIT */
-#define X86_FEATURE_MTRR	( 0*32+12) /* Memory Type Range Registers */
-#define X86_FEATURE_PGE		( 0*32+13) /* Page Global Enable */
-#define X86_FEATURE_MCA		( 0*32+14) /* Machine Check Architecture */
-#define X86_FEATURE_CMOV	( 0*32+15) /* CMOV instructions */
-					  /* (plus FCMOVcc, FCOMI with FPU) */
-#define X86_FEATURE_PAT		( 0*32+16) /* Page Attribute Table */
-#define X86_FEATURE_PSE36	( 0*32+17) /* 36-bit PSEs */
-#define X86_FEATURE_PN		( 0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLUSH	( 0*32+19) /* CLFLUSH instruction */
-#define X86_FEATURE_DS		( 0*32+21) /* "dts" Debug Store */
-#define X86_FEATURE_ACPI	( 0*32+22) /* ACPI via MSR */
-#define X86_FEATURE_MMX		( 0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR	( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
-#define X86_FEATURE_XMM		( 0*32+25) /* "sse" */
-#define X86_FEATURE_XMM2	( 0*32+26) /* "sse2" */
-#define X86_FEATURE_SELFSNOOP	( 0*32+27) /* "ss" CPU self snoop */
-#define X86_FEATURE_HT		( 0*32+28) /* Hyper-Threading */
-#define X86_FEATURE_ACC		( 0*32+29) /* "tm" Automatic clock control */
-#define X86_FEATURE_IA64	( 0*32+30) /* IA-64 processor */
-#define X86_FEATURE_PBE		( 0*32+31) /* Pending Break Enable */
-
-/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
-/* Don't duplicate feature flags which are redundant with Intel! */
-#define X86_FEATURE_SYSCALL	( 1*32+11) /* SYSCALL/SYSRET */
-#define X86_FEATURE_MP		( 1*32+19) /* MP Capable. */
-#define X86_FEATURE_NX		( 1*32+20) /* Execute Disable */
-#define X86_FEATURE_MMXEXT	( 1*32+22) /* AMD MMX extensions */
-#define X86_FEATURE_FXSR_OPT	( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
-#define X86_FEATURE_GBPAGES	( 1*32+26) /* "pdpe1gb" GB pages */
-#define X86_FEATURE_RDTSCP	( 1*32+27) /* RDTSCP */
-#define X86_FEATURE_LM		( 1*32+29) /* Long Mode (x86-64) */
-#define X86_FEATURE_3DNOWEXT	( 1*32+30) /* AMD 3DNow! extensions */
-#define X86_FEATURE_3DNOW	( 1*32+31) /* 3DNow! */
-
-/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
-#define X86_FEATURE_RECOVERY	( 2*32+ 0) /* CPU in recovery mode */
-#define X86_FEATURE_LONGRUN	( 2*32+ 1) /* Longrun power control */
-#define X86_FEATURE_LRTI	( 2*32+ 3) /* LongRun table interface */
-
-/* Other features, Linux-defined mapping, word 3 */
-/* This range is used for feature bits which conflict or are synthesized */
-#define X86_FEATURE_CXMMX	( 3*32+ 0) /* Cyrix MMX extensions */
-#define X86_FEATURE_K6_MTRR	( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
-#define X86_FEATURE_CYRIX_ARR	( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
-#define X86_FEATURE_CENTAUR_MCR	( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
-/* cpu types for specific tunings: */
-#define X86_FEATURE_K8		( 3*32+ 4) /* "" Opteron, Athlon64 */
-#define X86_FEATURE_K7		( 3*32+ 5) /* "" Athlon */
-#define X86_FEATURE_P3		( 3*32+ 6) /* "" P3 */
-#define X86_FEATURE_P4		( 3*32+ 7) /* "" P4 */
-#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
-#define X86_FEATURE_UP		( 3*32+ 9) /* smp kernel running on up */
-/* free, was #define X86_FEATURE_FXSAVE_LEAK ( 3*32+10) * "" FXSAVE leaks FOP/FIP/FOP */
-#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_PEBS	( 3*32+12) /* Precise-Event Based Sampling */
-#define X86_FEATURE_BTS		( 3*32+13) /* Branch Trace Store */
-#define X86_FEATURE_SYSCALL32	( 3*32+14) /* "" syscall in ia32 userspace */
-#define X86_FEATURE_SYSENTER32	( 3*32+15) /* "" sysenter in ia32 userspace */
-#define X86_FEATURE_REP_GOOD	( 3*32+16) /* rep microcode works well */
-#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */
-#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */
-/* free, was #define X86_FEATURE_11AP	( 3*32+19) * "" Bad local APIC aka 11AP */
-#define X86_FEATURE_NOPL	( 3*32+20) /* The NOPL (0F 1F) instructions */
-#define X86_FEATURE_ALWAYS	( 3*32+21) /* "" Always-present feature */
-#define X86_FEATURE_XTOPOLOGY	( 3*32+22) /* cpu topology enum extensions */
-#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
-#define X86_FEATURE_NONSTOP_TSC	( 3*32+24) /* TSC does not stop in C states */
-/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */
-#define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
-#define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
-#define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
-/* free, was #define X86_FEATURE_EAGER_FPU	( 3*32+29) * "eagerfpu" Non lazy FPU restore */
-#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
-
-/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
-#define X86_FEATURE_XMM3	( 4*32+ 0) /* "pni" SSE-3 */
-#define X86_FEATURE_PCLMULQDQ	( 4*32+ 1) /* PCLMULQDQ instruction */
-#define X86_FEATURE_DTES64	( 4*32+ 2) /* 64-bit Debug Store */
-#define X86_FEATURE_MWAIT	( 4*32+ 3) /* "monitor" Monitor/Mwait support */
-#define X86_FEATURE_DSCPL	( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
-#define X86_FEATURE_VMX		( 4*32+ 5) /* Hardware virtualization */
-#define X86_FEATURE_SMX		( 4*32+ 6) /* Safer mode */
-#define X86_FEATURE_EST		( 4*32+ 7) /* Enhanced SpeedStep */
-#define X86_FEATURE_TM2		( 4*32+ 8) /* Thermal Monitor 2 */
-#define X86_FEATURE_SSSE3	( 4*32+ 9) /* Supplemental SSE-3 */
-#define X86_FEATURE_CID		( 4*32+10) /* Context ID */
-#define X86_FEATURE_SDBG	( 4*32+11) /* Silicon Debug */
-#define X86_FEATURE_FMA		( 4*32+12) /* Fused multiply-add */
-#define X86_FEATURE_CX16	( 4*32+13) /* CMPXCHG16B */
-#define X86_FEATURE_XTPR	( 4*32+14) /* Send Task Priority Messages */
-#define X86_FEATURE_PDCM	( 4*32+15) /* Performance Capabilities */
-#define X86_FEATURE_PCID	( 4*32+17) /* Process Context Identifiers */
-#define X86_FEATURE_DCA		( 4*32+18) /* Direct Cache Access */
-#define X86_FEATURE_XMM4_1	( 4*32+19) /* "sse4_1" SSE-4.1 */
-#define X86_FEATURE_XMM4_2	( 4*32+20) /* "sse4_2" SSE-4.2 */
-#define X86_FEATURE_X2APIC	( 4*32+21) /* x2APIC */
-#define X86_FEATURE_MOVBE	( 4*32+22) /* MOVBE instruction */
-#define X86_FEATURE_POPCNT      ( 4*32+23) /* POPCNT instruction */
-#define X86_FEATURE_TSC_DEADLINE_TIMER	( 4*32+24) /* Tsc deadline timer */
-#define X86_FEATURE_AES		( 4*32+25) /* AES instructions */
-#define X86_FEATURE_XSAVE	( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
-#define X86_FEATURE_OSXSAVE	( 4*32+27) /* "" XSAVE enabled in the OS */
-#define X86_FEATURE_AVX		( 4*32+28) /* Advanced Vector Extensions */
-#define X86_FEATURE_F16C	( 4*32+29) /* 16-bit fp conversions */
-#define X86_FEATURE_RDRAND	( 4*32+30) /* The RDRAND instruction */
-#define X86_FEATURE_HYPERVISOR	( 4*32+31) /* Running on a hypervisor */
-
-/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
-#define X86_FEATURE_XSTORE	( 5*32+ 2) /* "rng" RNG present (xstore) */
-#define X86_FEATURE_XSTORE_EN	( 5*32+ 3) /* "rng_en" RNG enabled */
-#define X86_FEATURE_XCRYPT	( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
-#define X86_FEATURE_XCRYPT_EN	( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
-#define X86_FEATURE_ACE2	( 5*32+ 8) /* Advanced Cryptography Engine v2 */
-#define X86_FEATURE_ACE2_EN	( 5*32+ 9) /* ACE v2 enabled */
-#define X86_FEATURE_PHE		( 5*32+10) /* PadLock Hash Engine */
-#define X86_FEATURE_PHE_EN	( 5*32+11) /* PHE enabled */
-#define X86_FEATURE_PMM		( 5*32+12) /* PadLock Montgomery Multiplier */
-#define X86_FEATURE_PMM_EN	( 5*32+13) /* PMM enabled */
-
-/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
-#define X86_FEATURE_LAHF_LM	( 6*32+ 0) /* LAHF/SAHF in long mode */
-#define X86_FEATURE_CMP_LEGACY	( 6*32+ 1) /* If yes HyperThreading not valid */
-#define X86_FEATURE_SVM		( 6*32+ 2) /* Secure virtual machine */
-#define X86_FEATURE_EXTAPIC	( 6*32+ 3) /* Extended APIC space */
-#define X86_FEATURE_CR8_LEGACY	( 6*32+ 4) /* CR8 in 32-bit mode */
-#define X86_FEATURE_ABM		( 6*32+ 5) /* Advanced bit manipulation */
-#define X86_FEATURE_SSE4A	( 6*32+ 6) /* SSE-4A */
-#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */
-#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */
-#define X86_FEATURE_OSVW	( 6*32+ 9) /* OS Visible Workaround */
-#define X86_FEATURE_IBS		( 6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_XOP		( 6*32+11) /* extended AVX instructions */
-#define X86_FEATURE_SKINIT	( 6*32+12) /* SKINIT/STGI instructions */
-#define X86_FEATURE_WDT		( 6*32+13) /* Watchdog timer */
-#define X86_FEATURE_LWP		( 6*32+15) /* Light Weight Profiling */
-#define X86_FEATURE_FMA4	( 6*32+16) /* 4 operands MAC instructions */
-#define X86_FEATURE_TCE		( 6*32+17) /* translation cache extension */
-#define X86_FEATURE_NODEID_MSR	( 6*32+19) /* NodeId MSR */
-#define X86_FEATURE_TBM		( 6*32+21) /* trailing bit manipulations */
-#define X86_FEATURE_TOPOEXT	( 6*32+22) /* topology extensions CPUID leafs */
-#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */
-#define X86_FEATURE_PERFCTR_NB  ( 6*32+24) /* NB performance counter extensions */
-#define X86_FEATURE_BPEXT	(6*32+26) /* data breakpoint extension */
-#define X86_FEATURE_PERFCTR_L2	( 6*32+28) /* L2 performance counter extensions */
-#define X86_FEATURE_MWAITX	( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
-
-/*
- * Auxiliary flags: Linux defined - For features scattered in various
- * CPUID levels like 0x6, 0xA etc, word 7.
- *
- * Reuse free bits when adding new feature flags!
- */
-
-#define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
-#define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
-#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 4) /* Effectively INVPCID && CR4.PCIDE=1 */
-
-#define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
-#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
-
-#define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
-#define X86_FEATURE_RSB_CTXSW	( 7*32+19) /* Fill RSB on context switches */
-
-#define X86_FEATURE_RETPOLINE	( 7*32+29) /* Generic Retpoline mitigation for Spectre variant 2 */
-#define X86_FEATURE_RETPOLINE_AMD ( 7*32+30) /* AMD Retpoline mitigation for Spectre variant 2 */
-/* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */
-#define X86_FEATURE_KAISER	( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */
-
-/* Virtualization flags: Linux defined, word 8 */
-#define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
-#define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
-#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */
-#define X86_FEATURE_EPT         ( 8*32+ 3) /* Intel Extended Page Table */
-#define X86_FEATURE_VPID        ( 8*32+ 4) /* Intel Virtual Processor ID */
-
-#define X86_FEATURE_VMMCALL     ( 8*32+15) /* Prefer vmmcall to vmcall */
-#define X86_FEATURE_XENPV       ( 8*32+16) /* "" Xen paravirtual guest */
-
-
-/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
-#define X86_FEATURE_FSGSBASE	( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
-#define X86_FEATURE_TSC_ADJUST	( 9*32+ 1) /* TSC adjustment MSR 0x3b */
-#define X86_FEATURE_BMI1	( 9*32+ 3) /* 1st group bit manipulation extensions */
-#define X86_FEATURE_HLE		( 9*32+ 4) /* Hardware Lock Elision */
-#define X86_FEATURE_AVX2	( 9*32+ 5) /* AVX2 instructions */
-#define X86_FEATURE_SMEP	( 9*32+ 7) /* Supervisor Mode Execution Protection */
-#define X86_FEATURE_BMI2	( 9*32+ 8) /* 2nd group bit manipulation extensions */
-#define X86_FEATURE_ERMS	( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */
-#define X86_FEATURE_INVPCID	( 9*32+10) /* Invalidate Processor Context ID */
-#define X86_FEATURE_RTM		( 9*32+11) /* Restricted Transactional Memory */
-#define X86_FEATURE_CQM		( 9*32+12) /* Cache QoS Monitoring */
-#define X86_FEATURE_MPX		( 9*32+14) /* Memory Protection Extension */
-#define X86_FEATURE_AVX512F	( 9*32+16) /* AVX-512 Foundation */
-#define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
-#define X86_FEATURE_ADX		( 9*32+19) /* The ADCX and ADOX instructions */
-#define X86_FEATURE_SMAP	( 9*32+20) /* Supervisor Mode Access Prevention */
-#define X86_FEATURE_PCOMMIT	( 9*32+22) /* PCOMMIT instruction */
-#define X86_FEATURE_CLFLUSHOPT	( 9*32+23) /* CLFLUSHOPT instruction */
-#define X86_FEATURE_CLWB	( 9*32+24) /* CLWB instruction */
-#define X86_FEATURE_AVX512PF	( 9*32+26) /* AVX-512 Prefetch */
-#define X86_FEATURE_AVX512ER	( 9*32+27) /* AVX-512 Exponential and Reciprocal */
-#define X86_FEATURE_AVX512CD	( 9*32+28) /* AVX-512 Conflict Detection */
-#define X86_FEATURE_SHA_NI	( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
-
-/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */
-#define X86_FEATURE_XSAVEOPT	(10*32+ 0) /* XSAVEOPT */
-#define X86_FEATURE_XSAVEC	(10*32+ 1) /* XSAVEC */
-#define X86_FEATURE_XGETBV1	(10*32+ 2) /* XGETBV with ECX = 1 */
-#define X86_FEATURE_XSAVES	(10*32+ 3) /* XSAVES/XRSTORS */
-
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */
-#define X86_FEATURE_CQM_LLC	(11*32+ 1) /* LLC QoS if 1 */
-
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */
-#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */
-
-/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
-#define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
-
-/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
-#define X86_FEATURE_DTHERM	(14*32+ 0) /* Digital Thermal Sensor */
-#define X86_FEATURE_IDA		(14*32+ 1) /* Intel Dynamic Acceleration */
-#define X86_FEATURE_ARAT	(14*32+ 2) /* Always Running APIC Timer */
-#define X86_FEATURE_PLN		(14*32+ 4) /* Intel Power Limit Notification */
-#define X86_FEATURE_PTS		(14*32+ 6) /* Intel Package Thermal Status */
-#define X86_FEATURE_HWP		(14*32+ 7) /* Intel Hardware P-states */
-#define X86_FEATURE_HWP_NOTIFY	(14*32+ 8) /* HWP Notification */
-#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */
-#define X86_FEATURE_HWP_EPP	(14*32+10) /* HWP Energy Perf. Preference */
-#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */
-
-/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */
-#define X86_FEATURE_NPT		(15*32+ 0) /* Nested Page Table support */
-#define X86_FEATURE_LBRV	(15*32+ 1) /* LBR Virtualization support */
-#define X86_FEATURE_SVML	(15*32+ 2) /* "svm_lock" SVM locking MSR */
-#define X86_FEATURE_NRIPS	(15*32+ 3) /* "nrip_save" SVM next_rip save */
-#define X86_FEATURE_TSCRATEMSR  (15*32+ 4) /* "tsc_scale" TSC scaling support */
-#define X86_FEATURE_VMCBCLEAN   (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
-#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */
-#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */
-#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
-#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
-
-/*
- * BUG word(s)
- */
-#define X86_BUG(x)		(NCAPINTS*32 + (x))
-
-#define X86_BUG_F00F		X86_BUG(0) /* Intel F00F */
-#define X86_BUG_FDIV		X86_BUG(1) /* FPU FDIV */
-#define X86_BUG_COMA		X86_BUG(2) /* Cyrix 6x86 coma */
-#define X86_BUG_AMD_TLB_MMATCH	X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
-#define X86_BUG_AMD_APIC_C1E	X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
-#define X86_BUG_11AP		X86_BUG(5) /* Bad local APIC aka 11AP */
-#define X86_BUG_FXSAVE_LEAK	X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
-#define X86_BUG_CLFLUSH_MONITOR	X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
-#define X86_BUG_SYSRET_SS_ATTRS	X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
-#define X86_BUG_CPU_MELTDOWN	X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
-#define X86_BUG_SPECTRE_V1	X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
-#define X86_BUG_SPECTRE_V2	X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
+#include <asm/processor.h>
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
new file mode 100644
index 0000000..255ea74
--- /dev/null
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -0,0 +1,297 @@
+#ifndef _ASM_X86_CPUFEATURES_H
+#define _ASM_X86_CPUFEATURES_H
+
+#ifndef _ASM_X86_REQUIRED_FEATURES_H
+#include <asm/required-features.h>
+#endif
+
+#ifndef _ASM_X86_DISABLED_FEATURES_H
+#include <asm/disabled-features.h>
+#endif
+
+/*
+ * Defines x86 CPU feature bits
+ */
+#define NCAPINTS	16	/* N 32-bit words worth of info */
+#define NBUGINTS	1	/* N 32-bit bug flags */
+
+/*
+ * Note: If the comment begins with a quoted string, that string is used
+ * in /proc/cpuinfo instead of the macro name.  If the string is "",
+ * this feature bit is not displayed in /proc/cpuinfo at all.
+ */
+
+/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
+#define X86_FEATURE_FPU		( 0*32+ 0) /* Onboard FPU */
+#define X86_FEATURE_VME		( 0*32+ 1) /* Virtual Mode Extensions */
+#define X86_FEATURE_DE		( 0*32+ 2) /* Debugging Extensions */
+#define X86_FEATURE_PSE		( 0*32+ 3) /* Page Size Extensions */
+#define X86_FEATURE_TSC		( 0*32+ 4) /* Time Stamp Counter */
+#define X86_FEATURE_MSR		( 0*32+ 5) /* Model-Specific Registers */
+#define X86_FEATURE_PAE		( 0*32+ 6) /* Physical Address Extensions */
+#define X86_FEATURE_MCE		( 0*32+ 7) /* Machine Check Exception */
+#define X86_FEATURE_CX8		( 0*32+ 8) /* CMPXCHG8 instruction */
+#define X86_FEATURE_APIC	( 0*32+ 9) /* Onboard APIC */
+#define X86_FEATURE_SEP		( 0*32+11) /* SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR	( 0*32+12) /* Memory Type Range Registers */
+#define X86_FEATURE_PGE		( 0*32+13) /* Page Global Enable */
+#define X86_FEATURE_MCA		( 0*32+14) /* Machine Check Architecture */
+#define X86_FEATURE_CMOV	( 0*32+15) /* CMOV instructions */
+					  /* (plus FCMOVcc, FCOMI with FPU) */
+#define X86_FEATURE_PAT		( 0*32+16) /* Page Attribute Table */
+#define X86_FEATURE_PSE36	( 0*32+17) /* 36-bit PSEs */
+#define X86_FEATURE_PN		( 0*32+18) /* Processor serial number */
+#define X86_FEATURE_CLFLUSH	( 0*32+19) /* CLFLUSH instruction */
+#define X86_FEATURE_DS		( 0*32+21) /* "dts" Debug Store */
+#define X86_FEATURE_ACPI	( 0*32+22) /* ACPI via MSR */
+#define X86_FEATURE_MMX		( 0*32+23) /* Multimedia Extensions */
+#define X86_FEATURE_FXSR	( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+#define X86_FEATURE_XMM		( 0*32+25) /* "sse" */
+#define X86_FEATURE_XMM2	( 0*32+26) /* "sse2" */
+#define X86_FEATURE_SELFSNOOP	( 0*32+27) /* "ss" CPU self snoop */
+#define X86_FEATURE_HT		( 0*32+28) /* Hyper-Threading */
+#define X86_FEATURE_ACC		( 0*32+29) /* "tm" Automatic clock control */
+#define X86_FEATURE_IA64	( 0*32+30) /* IA-64 processor */
+#define X86_FEATURE_PBE		( 0*32+31) /* Pending Break Enable */
+
+/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
+/* Don't duplicate feature flags which are redundant with Intel! */
+#define X86_FEATURE_SYSCALL	( 1*32+11) /* SYSCALL/SYSRET */
+#define X86_FEATURE_MP		( 1*32+19) /* MP Capable. */
+#define X86_FEATURE_NX		( 1*32+20) /* Execute Disable */
+#define X86_FEATURE_MMXEXT	( 1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_FXSR_OPT	( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
+#define X86_FEATURE_GBPAGES	( 1*32+26) /* "pdpe1gb" GB pages */
+#define X86_FEATURE_RDTSCP	( 1*32+27) /* RDTSCP */
+#define X86_FEATURE_LM		( 1*32+29) /* Long Mode (x86-64) */
+#define X86_FEATURE_3DNOWEXT	( 1*32+30) /* AMD 3DNow! extensions */
+#define X86_FEATURE_3DNOW	( 1*32+31) /* 3DNow! */
+
+/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
+#define X86_FEATURE_RECOVERY	( 2*32+ 0) /* CPU in recovery mode */
+#define X86_FEATURE_LONGRUN	( 2*32+ 1) /* Longrun power control */
+#define X86_FEATURE_LRTI	( 2*32+ 3) /* LongRun table interface */
+
+/* Other features, Linux-defined mapping, word 3 */
+/* This range is used for feature bits which conflict or are synthesized */
+#define X86_FEATURE_CXMMX	( 3*32+ 0) /* Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR	( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR	( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR	( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
+/* cpu types for specific tunings: */
+#define X86_FEATURE_K8		( 3*32+ 4) /* "" Opteron, Athlon64 */
+#define X86_FEATURE_K7		( 3*32+ 5) /* "" Athlon */
+#define X86_FEATURE_P3		( 3*32+ 6) /* "" P3 */
+#define X86_FEATURE_P4		( 3*32+ 7) /* "" P4 */
+#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
+#define X86_FEATURE_UP		( 3*32+ 9) /* smp kernel running on up */
+/* free, was #define X86_FEATURE_FXSAVE_LEAK ( 3*32+10) * "" FXSAVE leaks FOP/FIP/FOP */
+#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
+#define X86_FEATURE_PEBS	( 3*32+12) /* Precise-Event Based Sampling */
+#define X86_FEATURE_BTS		( 3*32+13) /* Branch Trace Store */
+#define X86_FEATURE_SYSCALL32	( 3*32+14) /* "" syscall in ia32 userspace */
+#define X86_FEATURE_SYSENTER32	( 3*32+15) /* "" sysenter in ia32 userspace */
+#define X86_FEATURE_REP_GOOD	( 3*32+16) /* rep microcode works well */
+#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */
+#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */
+/* free, was #define X86_FEATURE_11AP	( 3*32+19) * "" Bad local APIC aka 11AP */
+#define X86_FEATURE_NOPL	( 3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_ALWAYS	( 3*32+21) /* "" Always-present feature */
+#define X86_FEATURE_XTOPOLOGY	( 3*32+22) /* cpu topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
+#define X86_FEATURE_NONSTOP_TSC	( 3*32+24) /* TSC does not stop in C states */
+/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */
+#define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
+#define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
+#define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
+/* free, was #define X86_FEATURE_EAGER_FPU	( 3*32+29) * "eagerfpu" Non lazy FPU restore */
+#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
+
+/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
+#define X86_FEATURE_XMM3	( 4*32+ 0) /* "pni" SSE-3 */
+#define X86_FEATURE_PCLMULQDQ	( 4*32+ 1) /* PCLMULQDQ instruction */
+#define X86_FEATURE_DTES64	( 4*32+ 2) /* 64-bit Debug Store */
+#define X86_FEATURE_MWAIT	( 4*32+ 3) /* "monitor" Monitor/Mwait support */
+#define X86_FEATURE_DSCPL	( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
+#define X86_FEATURE_VMX		( 4*32+ 5) /* Hardware virtualization */
+#define X86_FEATURE_SMX		( 4*32+ 6) /* Safer mode */
+#define X86_FEATURE_EST		( 4*32+ 7) /* Enhanced SpeedStep */
+#define X86_FEATURE_TM2		( 4*32+ 8) /* Thermal Monitor 2 */
+#define X86_FEATURE_SSSE3	( 4*32+ 9) /* Supplemental SSE-3 */
+#define X86_FEATURE_CID		( 4*32+10) /* Context ID */
+#define X86_FEATURE_SDBG	( 4*32+11) /* Silicon Debug */
+#define X86_FEATURE_FMA		( 4*32+12) /* Fused multiply-add */
+#define X86_FEATURE_CX16	( 4*32+13) /* CMPXCHG16B */
+#define X86_FEATURE_XTPR	( 4*32+14) /* Send Task Priority Messages */
+#define X86_FEATURE_PDCM	( 4*32+15) /* Performance Capabilities */
+#define X86_FEATURE_PCID	( 4*32+17) /* Process Context Identifiers */
+#define X86_FEATURE_DCA		( 4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_XMM4_1	( 4*32+19) /* "sse4_1" SSE-4.1 */
+#define X86_FEATURE_XMM4_2	( 4*32+20) /* "sse4_2" SSE-4.2 */
+#define X86_FEATURE_X2APIC	( 4*32+21) /* x2APIC */
+#define X86_FEATURE_MOVBE	( 4*32+22) /* MOVBE instruction */
+#define X86_FEATURE_POPCNT      ( 4*32+23) /* POPCNT instruction */
+#define X86_FEATURE_TSC_DEADLINE_TIMER	( 4*32+24) /* Tsc deadline timer */
+#define X86_FEATURE_AES		( 4*32+25) /* AES instructions */
+#define X86_FEATURE_XSAVE	( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
+#define X86_FEATURE_OSXSAVE	( 4*32+27) /* "" XSAVE enabled in the OS */
+#define X86_FEATURE_AVX		( 4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_F16C	( 4*32+29) /* 16-bit fp conversions */
+#define X86_FEATURE_RDRAND	( 4*32+30) /* The RDRAND instruction */
+#define X86_FEATURE_HYPERVISOR	( 4*32+31) /* Running on a hypervisor */
+
+/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
+#define X86_FEATURE_XSTORE	( 5*32+ 2) /* "rng" RNG present (xstore) */
+#define X86_FEATURE_XSTORE_EN	( 5*32+ 3) /* "rng_en" RNG enabled */
+#define X86_FEATURE_XCRYPT	( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
+#define X86_FEATURE_XCRYPT_EN	( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
+#define X86_FEATURE_ACE2	( 5*32+ 8) /* Advanced Cryptography Engine v2 */
+#define X86_FEATURE_ACE2_EN	( 5*32+ 9) /* ACE v2 enabled */
+#define X86_FEATURE_PHE		( 5*32+10) /* PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN	( 5*32+11) /* PHE enabled */
+#define X86_FEATURE_PMM		( 5*32+12) /* PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN	( 5*32+13) /* PMM enabled */
+
+/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
+#define X86_FEATURE_LAHF_LM	( 6*32+ 0) /* LAHF/SAHF in long mode */
+#define X86_FEATURE_CMP_LEGACY	( 6*32+ 1) /* If yes HyperThreading not valid */
+#define X86_FEATURE_SVM		( 6*32+ 2) /* Secure virtual machine */
+#define X86_FEATURE_EXTAPIC	( 6*32+ 3) /* Extended APIC space */
+#define X86_FEATURE_CR8_LEGACY	( 6*32+ 4) /* CR8 in 32-bit mode */
+#define X86_FEATURE_ABM		( 6*32+ 5) /* Advanced bit manipulation */
+#define X86_FEATURE_SSE4A	( 6*32+ 6) /* SSE-4A */
+#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */
+#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */
+#define X86_FEATURE_OSVW	( 6*32+ 9) /* OS Visible Workaround */
+#define X86_FEATURE_IBS		( 6*32+10) /* Instruction Based Sampling */
+#define X86_FEATURE_XOP		( 6*32+11) /* extended AVX instructions */
+#define X86_FEATURE_SKINIT	( 6*32+12) /* SKINIT/STGI instructions */
+#define X86_FEATURE_WDT		( 6*32+13) /* Watchdog timer */
+#define X86_FEATURE_LWP		( 6*32+15) /* Light Weight Profiling */
+#define X86_FEATURE_FMA4	( 6*32+16) /* 4 operands MAC instructions */
+#define X86_FEATURE_TCE		( 6*32+17) /* translation cache extension */
+#define X86_FEATURE_NODEID_MSR	( 6*32+19) /* NodeId MSR */
+#define X86_FEATURE_TBM		( 6*32+21) /* trailing bit manipulations */
+#define X86_FEATURE_TOPOEXT	( 6*32+22) /* topology extensions CPUID leafs */
+#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */
+#define X86_FEATURE_PERFCTR_NB  ( 6*32+24) /* NB performance counter extensions */
+#define X86_FEATURE_BPEXT	(6*32+26) /* data breakpoint extension */
+#define X86_FEATURE_PERFCTR_L2	( 6*32+28) /* L2 performance counter extensions */
+#define X86_FEATURE_MWAITX	( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
+
+/*
+ * Auxiliary flags: Linux defined - For features scattered in various
+ * CPUID levels like 0x6, 0xA etc, word 7.
+ *
+ * Reuse free bits when adding new feature flags!
+ */
+
+#define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
+#define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 4) /* Effectively INVPCID && CR4.PCIDE=1 */
+
+#define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
+#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
+
+#define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
+#define X86_FEATURE_RSB_CTXSW	( 7*32+19) /* Fill RSB on context switches */
+
+#define X86_FEATURE_RETPOLINE	( 7*32+29) /* Generic Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_AMD ( 7*32+30) /* AMD Retpoline mitigation for Spectre variant 2 */
+/* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */
+#define X86_FEATURE_KAISER	( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */
+
+/* Virtualization flags: Linux defined, word 8 */
+#define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
+#define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
+#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */
+#define X86_FEATURE_EPT         ( 8*32+ 3) /* Intel Extended Page Table */
+#define X86_FEATURE_VPID        ( 8*32+ 4) /* Intel Virtual Processor ID */
+
+#define X86_FEATURE_VMMCALL     ( 8*32+15) /* Prefer vmmcall to vmcall */
+#define X86_FEATURE_XENPV       ( 8*32+16) /* "" Xen paravirtual guest */
+
+
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
+#define X86_FEATURE_FSGSBASE	( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
+#define X86_FEATURE_TSC_ADJUST	( 9*32+ 1) /* TSC adjustment MSR 0x3b */
+#define X86_FEATURE_BMI1	( 9*32+ 3) /* 1st group bit manipulation extensions */
+#define X86_FEATURE_HLE		( 9*32+ 4) /* Hardware Lock Elision */
+#define X86_FEATURE_AVX2	( 9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_SMEP	( 9*32+ 7) /* Supervisor Mode Execution Protection */
+#define X86_FEATURE_BMI2	( 9*32+ 8) /* 2nd group bit manipulation extensions */
+#define X86_FEATURE_ERMS	( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */
+#define X86_FEATURE_INVPCID	( 9*32+10) /* Invalidate Processor Context ID */
+#define X86_FEATURE_RTM		( 9*32+11) /* Restricted Transactional Memory */
+#define X86_FEATURE_CQM		( 9*32+12) /* Cache QoS Monitoring */
+#define X86_FEATURE_MPX		( 9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_AVX512F	( 9*32+16) /* AVX-512 Foundation */
+#define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
+#define X86_FEATURE_ADX		( 9*32+19) /* The ADCX and ADOX instructions */
+#define X86_FEATURE_SMAP	( 9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_PCOMMIT	( 9*32+22) /* PCOMMIT instruction */
+#define X86_FEATURE_CLFLUSHOPT	( 9*32+23) /* CLFLUSHOPT instruction */
+#define X86_FEATURE_CLWB	( 9*32+24) /* CLWB instruction */
+#define X86_FEATURE_AVX512PF	( 9*32+26) /* AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER	( 9*32+27) /* AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD	( 9*32+28) /* AVX-512 Conflict Detection */
+#define X86_FEATURE_SHA_NI	( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
+
+/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */
+#define X86_FEATURE_XSAVEOPT	(10*32+ 0) /* XSAVEOPT */
+#define X86_FEATURE_XSAVEC	(10*32+ 1) /* XSAVEC */
+#define X86_FEATURE_XGETBV1	(10*32+ 2) /* XGETBV with ECX = 1 */
+#define X86_FEATURE_XSAVES	(10*32+ 3) /* XSAVES/XRSTORS */
+
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */
+#define X86_FEATURE_CQM_LLC	(11*32+ 1) /* LLC QoS if 1 */
+
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */
+#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */
+
+/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
+#define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
+
+/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
+#define X86_FEATURE_DTHERM	(14*32+ 0) /* Digital Thermal Sensor */
+#define X86_FEATURE_IDA		(14*32+ 1) /* Intel Dynamic Acceleration */
+#define X86_FEATURE_ARAT	(14*32+ 2) /* Always Running APIC Timer */
+#define X86_FEATURE_PLN		(14*32+ 4) /* Intel Power Limit Notification */
+#define X86_FEATURE_PTS		(14*32+ 6) /* Intel Package Thermal Status */
+#define X86_FEATURE_HWP		(14*32+ 7) /* Intel Hardware P-states */
+#define X86_FEATURE_HWP_NOTIFY	(14*32+ 8) /* HWP Notification */
+#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */
+#define X86_FEATURE_HWP_EPP	(14*32+10) /* HWP Energy Perf. Preference */
+#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */
+
+/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */
+#define X86_FEATURE_NPT		(15*32+ 0) /* Nested Page Table support */
+#define X86_FEATURE_LBRV	(15*32+ 1) /* LBR Virtualization support */
+#define X86_FEATURE_SVML	(15*32+ 2) /* "svm_lock" SVM locking MSR */
+#define X86_FEATURE_NRIPS	(15*32+ 3) /* "nrip_save" SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR  (15*32+ 4) /* "tsc_scale" TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN   (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
+
+/*
+ * BUG word(s)
+ */
+#define X86_BUG(x)		(NCAPINTS*32 + (x))
+
+#define X86_BUG_F00F		X86_BUG(0) /* Intel F00F */
+#define X86_BUG_FDIV		X86_BUG(1) /* FPU FDIV */
+#define X86_BUG_COMA		X86_BUG(2) /* Cyrix 6x86 coma */
+#define X86_BUG_AMD_TLB_MMATCH	X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
+#define X86_BUG_AMD_APIC_C1E	X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
+#define X86_BUG_11AP		X86_BUG(5) /* Bad local APIC aka 11AP */
+#define X86_BUG_FXSAVE_LEAK	X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
+#define X86_BUG_CLFLUSH_MONITOR	X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
+#define X86_BUG_SYSRET_SS_ATTRS	X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
+#define X86_BUG_CPU_MELTDOWN	X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
+#define X86_BUG_SPECTRE_V1	X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
+#define X86_BUG_SPECTRE_V2	X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
+
+#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 60c984a..94e7570 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -17,6 +17,7 @@
 #include <asm/user.h>
 #include <asm/fpu/api.h>
 #include <asm/fpu/xstate.h>
+#include <asm/cpufeature.h>
 
 /*
  * High level FPU state handling functions:
diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h
index 78162f8..d0afb05 100644
--- a/arch/x86/include/asm/irq_work.h
+++ b/arch/x86/include/asm/irq_work.h
@@ -1,7 +1,7 @@
 #ifndef _ASM_IRQ_WORK_H
 #define _ASM_IRQ_WORK_H
 
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 
 static inline bool arch_irq_work_has_interrupt(void)
 {
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index c70689b..0deeb2d 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -3,6 +3,8 @@
 
 #include <linux/sched.h>
 
+#include <asm/cpufeature.h>
+
 #define MWAIT_SUBSTATE_MASK		0xf
 #define MWAIT_CSTATE_MASK		0xf
 #define MWAIT_SUBSTATE_SIZE		4
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 249f1c7..8b91041 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -5,7 +5,7 @@
 
 #include <asm/alternative.h>
 #include <asm/alternative-asm.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 
 /*
  * Fill the CPU return stack buffer.
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 9e77cea..8e415cf 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -13,7 +13,7 @@ struct vm86;
 #include <asm/types.h>
 #include <uapi/asm/sigcontext.h>
 #include <asm/current.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/page.h>
 #include <asm/pgtable_types.h>
 #include <asm/percpu.h>
@@ -24,7 +24,6 @@ struct vm86;
 #include <asm/fpu/types.h>
 
 #include <linux/personality.h>
-#include <linux/cpumask.h>
 #include <linux/cache.h>
 #include <linux/threads.h>
 #include <linux/math64.h>
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index ba665eb..db33330 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -15,7 +15,7 @@
 
 #include <linux/stringify.h>
 #include <asm/nops.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 
 /* "Raw" instruction opcodes */
 #define __ASM_CLAC	.byte 0x0f,0x01,0xca
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index a438c55..04d6eef 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -16,7 +16,6 @@
 #endif
 #include <asm/thread_info.h>
 #include <asm/cpumask.h>
-#include <asm/cpufeature.h>
 
 extern int smp_num_siblings;
 extern unsigned int num_processors;
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 9b02820..18c9aaa 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -49,7 +49,7 @@
  */
 #ifndef __ASSEMBLY__
 struct task_struct;
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <linux/atomic.h>
 
 struct thread_info {
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index a691b66..e2a89d2 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -5,6 +5,7 @@
 #include <linux/sched.h>
 
 #include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/special_insns.h>
 #include <asm/smp.h>
 
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index f2f9b39..d83a55b 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -8,7 +8,7 @@
 #include <linux/errno.h>
 #include <linux/lockdep.h>
 #include <asm/alternative.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/page.h>
 
 /*
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 8f18461..924b657 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -62,7 +62,7 @@ ifdef CONFIG_X86_FEATURE_NAMES
 quiet_cmd_mkcapflags = MKCAP   $@
       cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $< $@
 
-cpufeature = $(src)/../../include/asm/cpufeature.h
+cpufeature = $(src)/../../include/asm/cpufeatures.h
 
 targets += capflags.c
 $(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.sh FORCE
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index ae20be6..6608c03 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -1,7 +1,7 @@
 #include <linux/bitops.h>
 #include <linux/kernel.h>
 
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/e820.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index aaf152e..15e47c1 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -8,6 +8,7 @@
 #include <linux/timer.h>
 #include <asm/pci-direct.h>
 #include <asm/tsc.h>
+#include <asm/cpufeature.h>
 
 #include "cpu.h"
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 565648b..9299e3b 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -8,7 +8,7 @@
 #include <linux/module.h>
 #include <linux/uaccess.h>
 
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/pgtable.h>
 #include <asm/msr.h>
 #include <asm/bugs.h>
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 3fa7231..3557b3c 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -14,7 +14,7 @@
 #include <linux/sysfs.h>
 #include <linux/pci.h>
 
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/amd_nb.h>
 #include <asm/smp.h>
 
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index afa9f0d..fbb5e90 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -1,5 +1,5 @@
 #include <asm/cpu_device_id.h>
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <linux/cpu.h>
 #include <linux/module.h>
 #include <linux/slab.h>
diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh
index 3f20710..6988c74 100644
--- a/arch/x86/kernel/cpu/mkcapflags.sh
+++ b/arch/x86/kernel/cpu/mkcapflags.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 #
-# Generate the x86_cap/bug_flags[] arrays from include/asm/cpufeature.h
+# Generate the x86_cap/bug_flags[] arrays from include/asm/cpufeatures.h
 #
 
 IN=$1
@@ -49,8 +49,8 @@ dump_array()
 trap 'rm "$OUT"' EXIT
 
 (
-	echo "#ifndef _ASM_X86_CPUFEATURE_H"
-	echo "#include <asm/cpufeature.h>"
+	echo "#ifndef _ASM_X86_CPUFEATURES_H"
+	echo "#include <asm/cpufeatures.h>"
 	echo "#endif"
 	echo ""
 
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index f924f41..49bd700 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -47,7 +47,7 @@
 #include <linux/smp.h>
 #include <linux/syscore_ops.h>
 
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/e820.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index 252da7a..a19a663 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -1,6 +1,6 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/msr.h>
 #include "cpu.h"
 
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 52a2526..19bc19d 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -24,6 +24,7 @@
 #include <asm/e820.h>
 #include <asm/proto.h>
 #include <asm/setup.h>
+#include <asm/cpufeature.h>
 
 /*
  * The e820 map is the map that gets modified e.g. with command line parameters
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 70284d3..1c0b49f 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -19,7 +19,7 @@
 #include <asm/setup.h>
 #include <asm/processor-flags.h>
 #include <asm/msr-index.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/percpu.h>
 #include <asm/nops.h>
 #include <asm/bootparam.h>
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index f48eb8e..3fdc1e5 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -12,6 +12,7 @@
 #include <linux/pm.h>
 #include <linux/io.h>
 
+#include <asm/cpufeature.h>
 #include <asm/irqdomain.h>
 #include <asm/fixmap.h>
 #include <asm/hpet.h>
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 113e707..f95ac5d 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -40,7 +40,7 @@
 #include <linux/uaccess.h>
 #include <linux/gfp.h>
 
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/msr.h>
 
 static struct class *msr_class;
diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S
index 4cf401f..b7c9db5 100644
--- a/arch/x86/kernel/verify_cpu.S
+++ b/arch/x86/kernel/verify_cpu.S
@@ -30,7 +30,7 @@
  * 	appropriately. Either display a message or halt.
  */
 
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/msr-index.h>
 
 verify_cpu:
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index a2fe51b..65be7cf 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,5 +1,5 @@
 #include <linux/linkage.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 /*
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index 009f982..24ef1c2 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -1,7 +1,7 @@
 /* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */
 
 #include <linux/linkage.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 /*
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 423644c..accf7f2 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -10,7 +10,7 @@
 #include <asm/current.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 16698bb..a0de849 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -1,7 +1,7 @@
 /* Copyright 2002 Andi Kleen */
 
 #include <linux/linkage.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 /*
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index ca2afdd..90ce01b 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -6,7 +6,7 @@
  *	- Copyright 2011 Fenghua Yu <fenghua.yu@intel.com>
  */
 #include <linux/linkage.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 #undef memmove
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 2661fad..c9c8122 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -1,7 +1,7 @@
 /* Copyright 2002 Andi Kleen, SuSE Labs */
 
 #include <linux/linkage.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 .weak memset
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 3d06b48..7bbb853 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -3,7 +3,7 @@
 #include <linux/stringify.h>
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 #include <asm-generic/export.h>
 #include <asm/nospec-branch.h>
diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c
index 92e2eac..f65a33f 100644
--- a/arch/x86/mm/setup_nx.c
+++ b/arch/x86/mm/setup_nx.c
@@ -4,6 +4,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/proto.h>
+#include <asm/cpufeature.h>
 
 static int disable_nx;
 
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index 50d86c0..660a83c 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -24,7 +24,6 @@
 #include <asm/nmi.h>
 #include <asm/apic.h>
 #include <asm/processor.h>
-#include <asm/cpufeature.h>
 
 #include "op_x86_model.h"
 #include "op_counter.h"
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index 755481f..764ac2f 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -3,7 +3,7 @@
 
 #include <asm/asm.h>
 #include <asm/segment.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/cmpxchg.h>
 #include <asm/nops.h>
 
diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c
index d51e25a..de67fea 100644
--- a/lib/atomic64_test.c
+++ b/lib/atomic64_test.c
@@ -17,7 +17,7 @@
 #include <linux/atomic.h>
 
 #ifdef CONFIG_X86
-#include <asm/processor.h>	/* for boot_cpu_has below */
+#include <asm/cpufeature.h>	/* for boot_cpu_has below */
 #endif
 
 #define TEST(bit, op, c_op, val)				\

[PATCH 4.4.y 008/101] x86/cpufeature: Replace the old static_cpu_has() with safe variant

[Srivatsa S. Bhat]

From: Borislav Petkov <bp@suse.de>

commit bc696ca05f5a8927329ec276a892341e006b00ba upstream

So the old one didn't work properly before alternatives had run.
And it was supposed to provide an optimized JMP because the
assumption was that the offset it is jumping to is within a
signed byte and thus a two-byte JMP.

So I did an x86_64 allyesconfig build and dumped all possible
sites where static_cpu_has() was used. The optimization amounted
to all in all 12(!) places where static_cpu_has() had generated
a 2-byte JMP. Which has saved us a whopping 36 bytes!

This clearly is not worth the trouble so we can remove it. The
only place where the optimization might count - in __switch_to()
- we will handle differently. But that's not subject of this
patch.

Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1453842730-28463-6-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/Kconfig.debug               |   10 ---
 arch/x86/include/asm/cpufeature.h    |  100 ++--------------------------------
 arch/x86/include/asm/fpu/internal.h  |   12 ++--
 arch/x86/kernel/apic/apic_numachip.c |    4 +
 arch/x86/kernel/cpu/common.c         |   12 +---
 arch/x86/kernel/vm86_32.c            |    2 -
 fs/btrfs/disk-io.c                   |    2 -
 7 files changed, 19 insertions(+), 123 deletions(-)

diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index da00fe1..2aa212f 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -367,16 +367,6 @@ config DEBUG_IMR_SELFTEST
 
 	  If unsure say N here.
 
-config X86_DEBUG_STATIC_CPU_HAS
-	bool "Debug alternatives"
-	depends on DEBUG_KERNEL
-	---help---
-	  This option causes additional code to be generated which
-	  fails if static_cpu_has() is used before alternatives have
-	  run.
-
-	  If unsure, say N.
-
 config X86_DEBUG_FPU
 	bool "Debug the x86 FPU code"
 	depends on DEBUG_KERNEL
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index f62e872..b60598c 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -127,103 +127,19 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 #define cpu_has_osxsave		boot_cpu_has(X86_FEATURE_OSXSAVE)
 #define cpu_has_hypervisor	boot_cpu_has(X86_FEATURE_HYPERVISOR)
 /*
- * Do not add any more of those clumsy macros - use static_cpu_has_safe() for
+ * Do not add any more of those clumsy macros - use static_cpu_has() for
  * fast paths and boot_cpu_has() otherwise!
  */
 
 #if __GNUC__ >= 4 && defined(CONFIG_X86_FAST_FEATURE_TESTS)
-extern void warn_pre_alternatives(void);
-extern bool __static_cpu_has_safe(u16 bit);
+extern bool __static_cpu_has(u16 bit);
 
 /*
  * Static testing of CPU features.  Used the same as boot_cpu_has().
  * These are only valid after alternatives have run, but will statically
  * patch the target code for additional performance.
  */
-static __always_inline __pure bool __static_cpu_has(u16 bit)
-{
-#ifdef CC_HAVE_ASM_GOTO
-
-#ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS
-
-		/*
-		 * Catch too early usage of this before alternatives
-		 * have run.
-		 */
-		asm_volatile_goto("1: jmp %l[t_warn]\n"
-			 "2:\n"
-			 ".section .altinstructions,\"a\"\n"
-			 " .long 1b - .\n"
-			 " .long 0\n"		/* no replacement */
-			 " .word %P0\n"		/* 1: do replace */
-			 " .byte 2b - 1b\n"	/* source len */
-			 " .byte 0\n"		/* replacement len */
-			 " .byte 0\n"		/* pad len */
-			 ".previous\n"
-			 /* skipping size check since replacement size = 0 */
-			 : : "i" (X86_FEATURE_ALWAYS) : : t_warn);
-
-#endif
-
-		asm_volatile_goto("1: jmp %l[t_no]\n"
-			 "2:\n"
-			 ".section .altinstructions,\"a\"\n"
-			 " .long 1b - .\n"
-			 " .long 0\n"		/* no replacement */
-			 " .word %P0\n"		/* feature bit */
-			 " .byte 2b - 1b\n"	/* source len */
-			 " .byte 0\n"		/* replacement len */
-			 " .byte 0\n"		/* pad len */
-			 ".previous\n"
-			 /* skipping size check since replacement size = 0 */
-			 : : "i" (bit) : : t_no);
-		return true;
-	t_no:
-		return false;
-
-#ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS
-	t_warn:
-		warn_pre_alternatives();
-		return false;
-#endif
-
-#else /* CC_HAVE_ASM_GOTO */
-
-		u8 flag;
-		/* Open-coded due to __stringify() in ALTERNATIVE() */
-		asm volatile("1: movb $0,%0\n"
-			     "2:\n"
-			     ".section .altinstructions,\"a\"\n"
-			     " .long 1b - .\n"
-			     " .long 3f - .\n"
-			     " .word %P1\n"		/* feature bit */
-			     " .byte 2b - 1b\n"		/* source len */
-			     " .byte 4f - 3f\n"		/* replacement len */
-			     " .byte 0\n"		/* pad len */
-			     ".previous\n"
-			     ".section .discard,\"aw\",@progbits\n"
-			     " .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */
-			     ".previous\n"
-			     ".section .altinstr_replacement,\"ax\"\n"
-			     "3: movb $1,%0\n"
-			     "4:\n"
-			     ".previous\n"
-			     : "=qm" (flag) : "i" (bit));
-		return flag;
-
-#endif /* CC_HAVE_ASM_GOTO */
-}
-
-#define static_cpu_has(bit)					\
-(								\
-	__builtin_constant_p(boot_cpu_has(bit)) ?		\
-		boot_cpu_has(bit) :				\
-	__builtin_constant_p(bit) ?				\
-		__static_cpu_has(bit) :				\
-		boot_cpu_has(bit)				\
-)
-
-static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
+static __always_inline __pure bool _static_cpu_has(u16 bit)
 {
 #ifdef CC_HAVE_ASM_GOTO
 		asm_volatile_goto("1: jmp %l[t_dynamic]\n"
@@ -257,7 +173,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
 	t_no:
 		return false;
 	t_dynamic:
-		return __static_cpu_has_safe(bit);
+		return __static_cpu_has(bit);
 #else
 		u8 flag;
 		/* Open-coded due to __stringify() in ALTERNATIVE() */
@@ -295,22 +211,21 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
 			     ".previous\n"
 			     : "=qm" (flag)
 			     : "i" (bit), "i" (X86_FEATURE_ALWAYS));
-		return (flag == 2 ? __static_cpu_has_safe(bit) : flag);
+		return (flag == 2 ? __static_cpu_has(bit) : flag);
 #endif /* CC_HAVE_ASM_GOTO */
 }
 
-#define static_cpu_has_safe(bit)				\
+#define static_cpu_has(bit)					\
 (								\
 	__builtin_constant_p(boot_cpu_has(bit)) ?		\
 		boot_cpu_has(bit) :				\
-		_static_cpu_has_safe(bit)			\
+		_static_cpu_has(bit)				\
 )
 #else
 /*
  * gcc 3.x is too stupid to do the static test; fall back to dynamic.
  */
 #define static_cpu_has(bit)		boot_cpu_has(bit)
-#define static_cpu_has_safe(bit)	boot_cpu_has(bit)
 #endif
 
 #define cpu_has_bug(c, bit)		cpu_has(c, (bit))
@@ -318,7 +233,6 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
 #define clear_cpu_bug(c, bit)		clear_cpu_cap(c, (bit))
 
 #define static_cpu_has_bug(bit)		static_cpu_has((bit))
-#define static_cpu_has_bug_safe(bit)	static_cpu_has_safe((bit))
 #define boot_cpu_has_bug(bit)		cpu_has_bug(&boot_cpu_data, (bit))
 
 #define MAX_CPU_FEATURES		(NCAPINTS * 32)
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 94e7570..ec2aedb 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -64,17 +64,17 @@ static __always_inline __pure bool use_eager_fpu(void)
 
 static __always_inline __pure bool use_xsaveopt(void)
 {
-	return static_cpu_has_safe(X86_FEATURE_XSAVEOPT);
+	return static_cpu_has(X86_FEATURE_XSAVEOPT);
 }
 
 static __always_inline __pure bool use_xsave(void)
 {
-	return static_cpu_has_safe(X86_FEATURE_XSAVE);
+	return static_cpu_has(X86_FEATURE_XSAVE);
 }
 
 static __always_inline __pure bool use_fxsr(void)
 {
-	return static_cpu_has_safe(X86_FEATURE_FXSR);
+	return static_cpu_has(X86_FEATURE_FXSR);
 }
 
 /*
@@ -301,7 +301,7 @@ static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate)
 
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	if (static_cpu_has_safe(X86_FEATURE_XSAVES))
+	if (static_cpu_has(X86_FEATURE_XSAVES))
 		XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
 	else
 		XSTATE_OP(XSAVE, xstate, lmask, hmask, err);
@@ -323,7 +323,7 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
 
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	if (static_cpu_has_safe(X86_FEATURE_XSAVES))
+	if (static_cpu_has(X86_FEATURE_XSAVES))
 		XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
 	else
 		XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
@@ -461,7 +461,7 @@ static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate)
 	 * pending. Clear the x87 state here by setting it to fixed values.
 	 * "m" is a random variable that should be in L1.
 	 */
-	if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) {
+	if (unlikely(static_cpu_has_bug(X86_BUG_FXSAVE_LEAK))) {
 		asm volatile(
 			"fnclex\n\t"
 			"emms\n\t"
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 2bd2292..bac0805 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -30,7 +30,7 @@ static unsigned int numachip1_get_apic_id(unsigned long x)
 	unsigned long value;
 	unsigned int id = (x >> 24) & 0xff;
 
-	if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) {
+	if (static_cpu_has(X86_FEATURE_NODEID_MSR)) {
 		rdmsrl(MSR_FAM10H_NODE_ID, value);
 		id |= (value << 2) & 0xff00;
 	}
@@ -178,7 +178,7 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
 	this_cpu_write(cpu_llc_id, node);
 
 	/* Account for nodes per socket in multi-core-module processors */
-	if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) {
+	if (static_cpu_has(X86_FEATURE_NODEID_MSR)) {
 		rdmsrl(MSR_FAM10H_NODE_ID, val);
 		nodes = ((val >> 3) & 7) + 1;
 	}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 5b6e43b..f31b26b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1576,19 +1576,11 @@ void cpu_init(void)
 }
 #endif
 
-#ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS
-void warn_pre_alternatives(void)
-{
-	WARN(1, "You're using static_cpu_has before alternatives have run!\n");
-}
-EXPORT_SYMBOL_GPL(warn_pre_alternatives);
-#endif
-
-inline bool __static_cpu_has_safe(u16 bit)
+inline bool __static_cpu_has(u16 bit)
 {
 	return boot_cpu_has(bit);
 }
-EXPORT_SYMBOL_GPL(__static_cpu_has_safe);
+EXPORT_SYMBOL_GPL(__static_cpu_has);
 
 static void bsp_resume(void)
 {
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index d6d64a5..7f4839e 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -358,7 +358,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 	/* make room for real-mode segments */
 	tsk->thread.sp0 += 16;
 
-	if (static_cpu_has_safe(X86_FEATURE_SEP))
+	if (static_cpu_has(X86_FEATURE_SEP))
 		tsk->thread.sysenter_cs = 0;
 
 	load_sp0(tss, &tsk->thread);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 7efd70b..d106b98 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -923,7 +923,7 @@ static int check_async_write(struct inode *inode, unsigned long bio_flags)
 	if (bio_flags & EXTENT_BIO_TREE_LOG)
 		return 0;
 #ifdef CONFIG_X86
-	if (static_cpu_has_safe(X86_FEATURE_XMM4_2))
+	if (static_cpu_has(X86_FEATURE_XMM4_2))
 		return 0;
 #endif
 	return 1;

[PATCH 4.4.y 009/101] x86/cpufeature: Get rid of the non-asm goto variant

[Srivatsa S. Bhat]

From: Borislav Petkov <bp@alien8.de>

commit a362bf9f5e7dd659b96d01382da7b855f4e5a7a1 upstream

I can simply quote hpa from the mail:

  "Get rid of the non-asm goto variant and just fall back to
   dynamic if asm goto is unavailable. It doesn't make any sense,
   really, if it is supposed to be safe, and by now the asm
   goto-capable gcc is in more wide use. (Originally the gcc 3.x
   fallback to pure dynamic didn't exist, either.)"

Booy, am I lazy.

Cleanup the whole CC_HAVE_ASM_GOTO ifdeffery too, while at it.

Suggested-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20160127084325.GB30712@pd.tnic
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeature.h |   49 ++++---------------------------------
 1 file changed, 5 insertions(+), 44 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index b60598c..53de461 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -131,17 +131,16 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
  * fast paths and boot_cpu_has() otherwise!
  */
 
-#if __GNUC__ >= 4 && defined(CONFIG_X86_FAST_FEATURE_TESTS)
+#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS)
 extern bool __static_cpu_has(u16 bit);
 
 /*
  * Static testing of CPU features.  Used the same as boot_cpu_has().
- * These are only valid after alternatives have run, but will statically
- * patch the target code for additional performance.
+ * These will statically patch the target code for additional
+ * performance.
  */
 static __always_inline __pure bool _static_cpu_has(u16 bit)
 {
-#ifdef CC_HAVE_ASM_GOTO
 		asm_volatile_goto("1: jmp %l[t_dynamic]\n"
 			 "2:\n"
 			 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
@@ -174,45 +173,6 @@ static __always_inline __pure bool _static_cpu_has(u16 bit)
 		return false;
 	t_dynamic:
 		return __static_cpu_has(bit);
-#else
-		u8 flag;
-		/* Open-coded due to __stringify() in ALTERNATIVE() */
-		asm volatile("1: movb $2,%0\n"
-			     "2:\n"
-			     ".section .altinstructions,\"a\"\n"
-			     " .long 1b - .\n"		/* src offset */
-			     " .long 3f - .\n"		/* repl offset */
-			     " .word %P2\n"		/* always replace */
-			     " .byte 2b - 1b\n"		/* source len */
-			     " .byte 4f - 3f\n"		/* replacement len */
-			     " .byte 0\n"		/* pad len */
-			     ".previous\n"
-			     ".section .discard,\"aw\",@progbits\n"
-			     " .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */
-			     ".previous\n"
-			     ".section .altinstr_replacement,\"ax\"\n"
-			     "3: movb $0,%0\n"
-			     "4:\n"
-			     ".previous\n"
-			     ".section .altinstructions,\"a\"\n"
-			     " .long 1b - .\n"		/* src offset */
-			     " .long 5f - .\n"		/* repl offset */
-			     " .word %P1\n"		/* feature bit */
-			     " .byte 4b - 3b\n"		/* src len */
-			     " .byte 6f - 5f\n"		/* repl len */
-			     " .byte 0\n"		/* pad len */
-			     ".previous\n"
-			     ".section .discard,\"aw\",@progbits\n"
-			     " .byte 0xff + (6f-5f) - (4b-3b)\n" /* size check */
-			     ".previous\n"
-			     ".section .altinstr_replacement,\"ax\"\n"
-			     "5: movb $1,%0\n"
-			     "6:\n"
-			     ".previous\n"
-			     : "=qm" (flag)
-			     : "i" (bit), "i" (X86_FEATURE_ALWAYS));
-		return (flag == 2 ? __static_cpu_has(bit) : flag);
-#endif /* CC_HAVE_ASM_GOTO */
 }
 
 #define static_cpu_has(bit)					\
@@ -223,7 +183,8 @@ static __always_inline __pure bool _static_cpu_has(u16 bit)
 )
 #else
 /*
- * gcc 3.x is too stupid to do the static test; fall back to dynamic.
+ * Fall back to dynamic for gcc versions which don't support asm goto. Should be
+ * a minority now anyway.
  */
 #define static_cpu_has(bit)		boot_cpu_has(bit)
 #endif

[PATCH 4.4.y 010/101] x86/alternatives: Add an auxilary section

[Srivatsa S. Bhat]

From: Borislav Petkov <bp@suse.de>

commit 337e4cc84021212a87b04b77b65cccc49304909e upstream

Add .altinstr_aux for additional instructions which will be used
before and/or during patching. All stuff which needs more
sophisticated patching should go there. See next patch.

Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1453842730-28463-8-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/vmlinux.lds.S |   11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index e065065..a703842 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -202,6 +202,17 @@ SECTIONS
 	:init
 #endif
 
+	/*
+	 * Section for code used exclusively before alternatives are run. All
+	 * references to such code must be patched out by alternatives, normally
+	 * by using X86_FEATURE_ALWAYS CPU feature bit.
+	 *
+	 * See static_cpu_has() for an example.
+	 */
+	.altinstr_aux : AT(ADDR(.altinstr_aux) - LOAD_OFFSET) {
+		*(.altinstr_aux)
+	}
+
 	INIT_DATA_SECTION(16)
 
 	.x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {

[PATCH 4.4.y 011/101] x86/alternatives: Discard dynamic check after init

[Srivatsa S. Bhat]

From: Brian Gerst <brgerst@gmail.com>

commit 2476f2fa20568bd5d9e09cd35bcd73e99a6f4cc6 upstream

Move the code to do the dynamic check to the altinstr_aux
section so that it is discarded after alternatives have run and
a static branch has been chosen.

This way we're changing the dynamic branch from C code to
assembly, which makes it *substantially* smaller while avoiding
a completely unnecessary call to an out of line function.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
[ Changed it to do TESTB, as hpa suggested. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Young <dyoung@redhat.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kristen Carlson Accardi <kristen@linux.intel.com>
Cc: Laura Abbott <labbott@fedoraproject.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1452972124-7380-1-git-send-email-brgerst@gmail.com
Link: http://lkml.kernel.org/r/20160127084525.GC30712@pd.tnic
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeature.h |   19 ++++++++++++-------
 arch/x86/kernel/cpu/common.c      |    6 ------
 2 files changed, 12 insertions(+), 13 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 53de461..1c9d6c5 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -132,8 +132,6 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
  */
 
 #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS)
-extern bool __static_cpu_has(u16 bit);
-
 /*
  * Static testing of CPU features.  Used the same as boot_cpu_has().
  * These will statically patch the target code for additional
@@ -141,7 +139,7 @@ extern bool __static_cpu_has(u16 bit);
  */
 static __always_inline __pure bool _static_cpu_has(u16 bit)
 {
-		asm_volatile_goto("1: jmp %l[t_dynamic]\n"
+		asm_volatile_goto("1: jmp 6f\n"
 			 "2:\n"
 			 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
 			         "((5f-4f) - (2b-1b)),0x90\n"
@@ -166,13 +164,20 @@ static __always_inline __pure bool _static_cpu_has(u16 bit)
 			 " .byte 0\n"			/* repl len */
 			 " .byte 0\n"			/* pad len */
 			 ".previous\n"
-			 : : "i" (bit), "i" (X86_FEATURE_ALWAYS)
-			 : : t_dynamic, t_no);
+			 ".section .altinstr_aux,\"ax\"\n"
+			 "6:\n"
+			 " testb %[bitnum],%[cap_byte]\n"
+			 " jnz %l[t_yes]\n"
+			 " jmp %l[t_no]\n"
+			 ".previous\n"
+			 : : "i" (bit), "i" (X86_FEATURE_ALWAYS),
+			     [bitnum] "i" (1 << (bit & 7)),
+			     [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3])
+			 : : t_yes, t_no);
+	t_yes:
 		return true;
 	t_no:
 		return false;
-	t_dynamic:
-		return __static_cpu_has(bit);
 }
 
 #define static_cpu_has(bit)					\
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f31b26b..58d56c4 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1576,12 +1576,6 @@ void cpu_init(void)
 }
 #endif
 
-inline bool __static_cpu_has(u16 bit)
-{
-	return boot_cpu_has(bit);
-}
-EXPORT_SYMBOL_GPL(__static_cpu_has);
-
 static void bsp_resume(void)
 {
 	if (this_cpu->c_bsp_resume)

[PATCH 4.4.y 012/101] x86/vdso: Use static_cpu_has()

[Srivatsa S. Bhat]

From: Borislav Petkov <bp@suse.de>

commit 8c725306993198f845038dc9e45a1267099867a6 upstream

... and simplify and speed up a tad.

Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1453842730-28463-10-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/entry/vdso/vma.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 5471ac3..6b46648 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -255,7 +255,7 @@ static void vgetcpu_cpu_init(void *arg)
 #ifdef CONFIG_NUMA
 	node = cpu_to_node(cpu);
 #endif
-	if (cpu_has(&cpu_data(cpu), X86_FEATURE_RDTSCP))
+	if (static_cpu_has(X86_FEATURE_RDTSCP))
 		write_rdtscp_aux((node << 12) | cpu);
 
 	/*

[PATCH 4.4.y 013/101] x86/boot: Simplify kernel load address alignment check

[Srivatsa S. Bhat]

From: Alexander Kuleshov <kuleshovmail@gmail.com>

commit a4733143085d6c782ac1e6c85778655b6bac1d4e upstream

We are using %rax as temporary register to check the kernel
address alignment. We don't really have to since the TEST
instruction does not clobber the destination operand.

Suggested-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Alexander Kuleshov <kuleshovmail@gmail.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Alexander Popov <alpopov@ptsecurity.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1453531828-19291-1-git-send-email-kuleshovmail@gmail.com
Link: http://lkml.kernel.org/r/1453842730-28463-11-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/head_64.S |    4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 4034e90..734ba1d 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -76,9 +76,7 @@ startup_64:
 	subq	$_text - __START_KERNEL_map, %rbp
 
 	/* Is the address not 2M aligned? */
-	movq	%rbp, %rax
-	andl	$~PMD_PAGE_MASK, %eax
-	testl	%eax, %eax
+	testl	$~PMD_PAGE_MASK, %ebp
 	jnz	bad_address
 
 	/*

[PATCH 4.4.y 014/101] x86/cpufeature: Speed up cpu_feature_enabled()

[Srivatsa S. Bhat]

From: Borislav Petkov <bp@suse.de>

commit f2cc8e0791c70833758101d9756609a08dd601ec upstream

When GCC cannot do constant folding for this macro, it falls back to
cpu_has(). But static_cpu_has() is optimal and it works at all times
now. So use it and speedup the fallback case.

Before we had this:

  mov    0x99d674(%rip),%rdx        # ffffffff81b0d9f4 <boot_cpu_data+0x34>
  shr    $0x2e,%rdx
  and    $0x1,%edx
  jne    ffffffff811704e9 <do_munmap+0x3f9>

After alternatives patching, it turns into:

		  jmp    0xffffffff81170390
		  nopl   (%rax)
		  ...
		  callq  ffffffff81056e00 <mpx_notify_unmap>
ffffffff81170390: mov    0x170(%r12),%rdi

Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1455578358-28347-1-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeature.h |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 1c9d6c5..03ca602 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -88,8 +88,7 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
  * is not relevant.
  */
 #define cpu_feature_enabled(bit)	\
-	(__builtin_constant_p(bit) && DISABLED_MASK_BIT_SET(bit) ? 0 :	\
-	 cpu_has(&boot_cpu_data, bit))
+	(__builtin_constant_p(bit) && DISABLED_MASK_BIT_SET(bit) ? 0 : static_cpu_has(bit))
 
 #define boot_cpu_has(bit)	cpu_has(&boot_cpu_data, bit)
 

[PATCH 4.4.y 015/101] x86/cpufeature, x86/mm/pkeys: Add protection keys related CPUID definitions

[Srivatsa S. Bhat]

From: Dave Hansen <dave.hansen@linux.intel.com>

commit dfb4a70f20c5b3880da56ee4c9484bdb4e8f1e65 upstream

There are two CPUID bits for protection keys.  One is for whether
the CPU contains the feature, and the other will appear set once
the OS enables protection keys.  Specifically:

	Bit 04: OSPKE. If 1, OS has set CR4.PKE to enable
	Protection keys (and the RDPKRU/WRPKRU instructions)

This is because userspace can not see CR4 contents, but it can
see CPUID contents.

X86_FEATURE_PKU is referred to as "PKU" in the hardware documentation:

	CPUID.(EAX=07H,ECX=0H):ECX.PKU [bit 3]

X86_FEATURE_OSPKE is "OSPKU":

	CPUID.(EAX=07H,ECX=0H):ECX.OSPKE [bit 4]

These are the first CPU features which need to look at the
ECX word in CPUID leaf 0x7, so this patch also includes
fetching that word in to the cpuinfo->x86_capability[] array.

Add it to the disabled-features mask when its config option is
off.  Even though we are not using it here, we also extend the
REQUIRED_MASK_BIT_SET() macro to keep it mirroring the
DISABLED_MASK_BIT_SET() version.

This means that in almost all code, you should use:

	cpu_has(c, X86_FEATURE_PKU)

and *not* the CONFIG option.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/20160212210201.7714C250@viggo.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeature.h        |   59 ++++++++++++++++++++----------
 arch/x86/include/asm/cpufeatures.h       |    2 +
 arch/x86/include/asm/disabled-features.h |   15 ++++++++
 arch/x86/include/asm/required-features.h |    7 ++++
 arch/x86/kernel/cpu/common.c             |    1 +
 5 files changed, 63 insertions(+), 21 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 03ca602..7fdd717 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -26,6 +26,7 @@ enum cpuid_leafs
 	CPUID_8000_0008_EBX,
 	CPUID_6_EAX,
 	CPUID_8000_000A_EDX,
+	CPUID_7_ECX,
 };
 
 #ifdef CONFIG_X86_FEATURE_NAMES
@@ -48,28 +49,42 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	 test_bit(bit, (unsigned long *)((c)->x86_capability))
 
 #define REQUIRED_MASK_BIT_SET(bit)					\
-	 ( (((bit)>>5)==0 && (1UL<<((bit)&31) & REQUIRED_MASK0)) ||	\
-	   (((bit)>>5)==1 && (1UL<<((bit)&31) & REQUIRED_MASK1)) ||	\
-	   (((bit)>>5)==2 && (1UL<<((bit)&31) & REQUIRED_MASK2)) ||	\
-	   (((bit)>>5)==3 && (1UL<<((bit)&31) & REQUIRED_MASK3)) ||	\
-	   (((bit)>>5)==4 && (1UL<<((bit)&31) & REQUIRED_MASK4)) ||	\
-	   (((bit)>>5)==5 && (1UL<<((bit)&31) & REQUIRED_MASK5)) ||	\
-	   (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) ||	\
-	   (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) ||	\
-	   (((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) ||	\
-	   (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) )
+	 ( (((bit)>>5)==0  && (1UL<<((bit)&31) & REQUIRED_MASK0 )) ||	\
+	   (((bit)>>5)==1  && (1UL<<((bit)&31) & REQUIRED_MASK1 )) ||	\
+	   (((bit)>>5)==2  && (1UL<<((bit)&31) & REQUIRED_MASK2 )) ||	\
+	   (((bit)>>5)==3  && (1UL<<((bit)&31) & REQUIRED_MASK3 )) ||	\
+	   (((bit)>>5)==4  && (1UL<<((bit)&31) & REQUIRED_MASK4 )) ||	\
+	   (((bit)>>5)==5  && (1UL<<((bit)&31) & REQUIRED_MASK5 )) ||	\
+	   (((bit)>>5)==6  && (1UL<<((bit)&31) & REQUIRED_MASK6 )) ||	\
+	   (((bit)>>5)==7  && (1UL<<((bit)&31) & REQUIRED_MASK7 )) ||	\
+	   (((bit)>>5)==8  && (1UL<<((bit)&31) & REQUIRED_MASK8 )) ||	\
+	   (((bit)>>5)==9  && (1UL<<((bit)&31) & REQUIRED_MASK9 )) ||	\
+	   (((bit)>>5)==10 && (1UL<<((bit)&31) & REQUIRED_MASK10)) ||	\
+	   (((bit)>>5)==11 && (1UL<<((bit)&31) & REQUIRED_MASK11)) ||	\
+	   (((bit)>>5)==12 && (1UL<<((bit)&31) & REQUIRED_MASK12)) ||	\
+	   (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK13)) ||	\
+	   (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK14)) ||	\
+	   (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK15)) ||	\
+	   (((bit)>>5)==14 && (1UL<<((bit)&31) & REQUIRED_MASK16)) )
 
 #define DISABLED_MASK_BIT_SET(bit)					\
-	 ( (((bit)>>5)==0 && (1UL<<((bit)&31) & DISABLED_MASK0)) ||	\
-	   (((bit)>>5)==1 && (1UL<<((bit)&31) & DISABLED_MASK1)) ||	\
-	   (((bit)>>5)==2 && (1UL<<((bit)&31) & DISABLED_MASK2)) ||	\
-	   (((bit)>>5)==3 && (1UL<<((bit)&31) & DISABLED_MASK3)) ||	\
-	   (((bit)>>5)==4 && (1UL<<((bit)&31) & DISABLED_MASK4)) ||	\
-	   (((bit)>>5)==5 && (1UL<<((bit)&31) & DISABLED_MASK5)) ||	\
-	   (((bit)>>5)==6 && (1UL<<((bit)&31) & DISABLED_MASK6)) ||	\
-	   (((bit)>>5)==7 && (1UL<<((bit)&31) & DISABLED_MASK7)) ||	\
-	   (((bit)>>5)==8 && (1UL<<((bit)&31) & DISABLED_MASK8)) ||	\
-	   (((bit)>>5)==9 && (1UL<<((bit)&31) & DISABLED_MASK9)) )
+	 ( (((bit)>>5)==0  && (1UL<<((bit)&31) & DISABLED_MASK0 )) ||	\
+	   (((bit)>>5)==1  && (1UL<<((bit)&31) & DISABLED_MASK1 )) ||	\
+	   (((bit)>>5)==2  && (1UL<<((bit)&31) & DISABLED_MASK2 )) ||	\
+	   (((bit)>>5)==3  && (1UL<<((bit)&31) & DISABLED_MASK3 )) ||	\
+	   (((bit)>>5)==4  && (1UL<<((bit)&31) & DISABLED_MASK4 )) ||	\
+	   (((bit)>>5)==5  && (1UL<<((bit)&31) & DISABLED_MASK5 )) ||	\
+	   (((bit)>>5)==6  && (1UL<<((bit)&31) & DISABLED_MASK6 )) ||	\
+	   (((bit)>>5)==7  && (1UL<<((bit)&31) & DISABLED_MASK7 )) ||	\
+	   (((bit)>>5)==8  && (1UL<<((bit)&31) & DISABLED_MASK8 )) ||	\
+	   (((bit)>>5)==9  && (1UL<<((bit)&31) & DISABLED_MASK9 )) ||	\
+	   (((bit)>>5)==10 && (1UL<<((bit)&31) & DISABLED_MASK10)) ||	\
+	   (((bit)>>5)==11 && (1UL<<((bit)&31) & DISABLED_MASK11)) ||	\
+	   (((bit)>>5)==12 && (1UL<<((bit)&31) & DISABLED_MASK12)) ||	\
+	   (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK13)) ||	\
+	   (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK14)) ||	\
+	   (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK15)) ||	\
+	   (((bit)>>5)==14 && (1UL<<((bit)&31) & DISABLED_MASK16)) )
 
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
@@ -79,6 +94,10 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : 	\
 	 x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability))
 
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
+#define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
+#define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
+
 /*
  * This macro is for detection of features which need kernel
  * infrastructure to be used.  It may *not* directly test the CPU
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 255ea74..6ebb4c2d 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -12,7 +12,7 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS	16	/* N 32-bit words worth of info */
+#define NCAPINTS	17	/* N 32-bit words worth of info */
 #define NBUGINTS	1	/* N 32-bit bug flags */
 
 /*
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 8b17c2a..522a069 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -30,6 +30,14 @@
 # define DISABLE_PCID		(1<<(X86_FEATURE_PCID & 31))
 #endif /* CONFIG_X86_64 */
 
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+# define DISABLE_PKU		(1<<(X86_FEATURE_PKU))
+# define DISABLE_OSPKE		(1<<(X86_FEATURE_OSPKE))
+#else
+# define DISABLE_PKU		0
+# define DISABLE_OSPKE		0
+#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -43,5 +51,12 @@
 #define DISABLED_MASK7	0
 #define DISABLED_MASK8	0
 #define DISABLED_MASK9	(DISABLE_MPX)
+#define DISABLED_MASK10	0
+#define DISABLED_MASK11	0
+#define DISABLED_MASK12	0
+#define DISABLED_MASK13	0
+#define DISABLED_MASK14	0
+#define DISABLED_MASK15	0
+#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index 5c6e4fb..4916144 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -92,5 +92,12 @@
 #define REQUIRED_MASK7	0
 #define REQUIRED_MASK8	0
 #define REQUIRED_MASK9	0
+#define REQUIRED_MASK10	0
+#define REQUIRED_MASK11	0
+#define REQUIRED_MASK12	0
+#define REQUIRED_MASK13	0
+#define REQUIRED_MASK14	0
+#define REQUIRED_MASK15	0
+#define REQUIRED_MASK16	0
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 58d56c4..d6a7b6f2 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -693,6 +693,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_7_0_EBX] = ebx;
 
 		c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006);
+		c->x86_capability[CPUID_7_ECX] = ecx;
 	}
 
 	/* Extended state features: level 0x0000000d */

[PATCH 4.4.y 016/101] x86/mm/pkeys: Fix mismerge of protection keys CPUID bits

[Srivatsa S. Bhat]

From: Dave Hansen <dave.hansen@linux.intel.com>

commit 0d47638f80a02b15869f1fe1fc09e5bf996750fd upstream

Kirill Shutemov pointed this out to me.

The tip tree currently has commit:

	dfb4a70f2 [x86/cpufeature, x86/mm/pkeys: Add protection keys related CPUID definitions]

whioch added support for two new CPUID bits: X86_FEATURE_PKU and
X86_FEATURE_OSPKE.  But, those bits were mis-merged and put in
cpufeature.h instead of cpufeatures.h.

This didn't cause any breakage *except* it keeps the "ospke" and
"pku" bits from showing up in cpuinfo.

Now cpuinfo has the two new flags:

	flags	: ...  pku ospke

BTW, is it really wise to have cpufeature.h and cpufeatures.h?
It seems like they can only cause confusion and mahem with tab
completion.

Reported-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Borislav Petkov <bp@suse.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave@sr71.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20160310221213.06F9DB53@viggo.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeature.h  |    4 ----
 arch/x86/include/asm/cpufeatures.h |    4 ++++
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 7fdd717..b953fb7 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -94,10 +94,6 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : 	\
 	 x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability))
 
-/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
-#define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
-#define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
-
 /*
  * This macro is for detection of features which need kernel
  * infrastructure to be used.  It may *not* directly test the CPU
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 6ebb4c2d..f19b901 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -276,6 +276,10 @@
 #define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
 #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
 
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
+#define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
+#define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
+
 /*
  * BUG word(s)
  */

[PATCH 4.4.y 017/101] x86/cpu: Add detection of AMD RAS Capabilities

[Srivatsa S. Bhat]

From: Yazen Ghannam <Yazen.Ghannam@amd.com>

commit 71faad43060d3d2040583635fbf7d1bdb3d04118 upstream

Add a new CPUID leaf to hold the contents of CPUID 0x80000007_EBX (RasCap).

Define bits that are currently in use:

 Bit 0: McaOverflowRecov
 Bit 1: SUCCOR
 Bit 3: ScalableMca

Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com>
[ Shorten comment. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: http://lkml.kernel.org/r/1462971509-3856-5-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeature.h  |    1 +
 arch/x86/include/asm/cpufeatures.h |    7 ++++++-
 arch/x86/kernel/cpu/common.c       |   10 +++++++---
 3 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index b953fb7..1d02ad6 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -27,6 +27,7 @@ enum cpuid_leafs
 	CPUID_6_EAX,
 	CPUID_8000_000A_EDX,
 	CPUID_7_ECX,
+	CPUID_8000_0007_EBX,
 };
 
 #ifdef CONFIG_X86_FEATURE_NAMES
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index f19b901..205ce70 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -12,7 +12,7 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS	17	/* N 32-bit words worth of info */
+#define NCAPINTS	18	/* N 32-bit words worth of info */
 #define NBUGINTS	1	/* N 32-bit bug flags */
 
 /*
@@ -280,6 +280,11 @@
 #define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
 #define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
 
+/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
+#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
+#define X86_FEATURE_SUCCOR	(17*32+1) /* Uncorrectable error containment and recovery */
+#define X86_FEATURE_SMCA	(17*32+3) /* Scalable MCA */
+
 /*
  * BUG word(s)
  */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index d6a7b6f2..814276d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -741,6 +741,13 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		}
 	}
 
+	if (c->extended_cpuid_level >= 0x80000007) {
+		cpuid(0x80000007, &eax, &ebx, &ecx, &edx);
+
+		c->x86_capability[CPUID_8000_0007_EBX] = ebx;
+		c->x86_power = edx;
+	}
+
 	if (c->extended_cpuid_level >= 0x80000008) {
 		cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
 
@@ -753,9 +760,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_phys_bits = 36;
 #endif
 
-	if (c->extended_cpuid_level >= 0x80000007)
-		c->x86_power = cpuid_edx(0x80000007);
-
 	if (c->extended_cpuid_level >= 0x8000000a)
 		c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
 

[PATCH 4.4.y 018/101] x86/cpufeature, x86/mm/pkeys: Fix broken compile-time disabling of pkeys

[Srivatsa S. Bhat]

From: Dave Hansen <dave.hansen@linux.intel.com>

commit e8df1a95b685af84a81698199ee206e0e66a8b44 upstream

When I added support for the Memory Protection Keys processor
feature, I had to reindent the REQUIRED/DISABLED_MASK macros, and
also consult the later cpufeature words.

I'm not quite sure how I bungled it, but I consulted the wrong
word at the end.  This only affected required or disabled cpu
features in cpufeature words 14, 15 and 16.  So, only Protection
Keys itself was screwed over here.

The result was that if you disabled pkeys in your .config, you
might still see some code show up that should have been compiled
out.  There should be no functional problems, though.

In verifying this patch I also realized that the DISABLE_PKU/OSPKE
macros were defined backwards and that the cpu_has() check in
setup_pku() was not doing the compile-time disabled checks.

So also fix the macro for DISABLE_PKU/OSPKE and add a compile-time
check for pkeys being enabled in setup_pku().

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: <stable@vger.kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Fixes: dfb4a70f20c5 ("x86/cpufeature, x86/mm/pkeys: Add protection keys related CPUID definitions")
Link: http://lkml.kernel.org/r/20160513221328.C200930B@viggo.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeature.h        |   12 ++++++------
 arch/x86/include/asm/disabled-features.h |    6 +++---
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 1d02ad6..aa7785e 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -64,9 +64,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   (((bit)>>5)==11 && (1UL<<((bit)&31) & REQUIRED_MASK11)) ||	\
 	   (((bit)>>5)==12 && (1UL<<((bit)&31) & REQUIRED_MASK12)) ||	\
 	   (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK13)) ||	\
-	   (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK14)) ||	\
-	   (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK15)) ||	\
-	   (((bit)>>5)==14 && (1UL<<((bit)&31) & REQUIRED_MASK16)) )
+	   (((bit)>>5)==14 && (1UL<<((bit)&31) & REQUIRED_MASK14)) ||	\
+	   (((bit)>>5)==15 && (1UL<<((bit)&31) & REQUIRED_MASK15)) ||	\
+	   (((bit)>>5)==16 && (1UL<<((bit)&31) & REQUIRED_MASK16)) )
 
 #define DISABLED_MASK_BIT_SET(bit)					\
 	 ( (((bit)>>5)==0  && (1UL<<((bit)&31) & DISABLED_MASK0 )) ||	\
@@ -83,9 +83,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   (((bit)>>5)==11 && (1UL<<((bit)&31) & DISABLED_MASK11)) ||	\
 	   (((bit)>>5)==12 && (1UL<<((bit)&31) & DISABLED_MASK12)) ||	\
 	   (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK13)) ||	\
-	   (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK14)) ||	\
-	   (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK15)) ||	\
-	   (((bit)>>5)==14 && (1UL<<((bit)&31) & DISABLED_MASK16)) )
+	   (((bit)>>5)==14 && (1UL<<((bit)&31) & DISABLED_MASK14)) ||	\
+	   (((bit)>>5)==15 && (1UL<<((bit)&31) & DISABLED_MASK15)) ||	\
+	   (((bit)>>5)==16 && (1UL<<((bit)&31) & DISABLED_MASK16)) )
 
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 522a069..0403b22 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -31,11 +31,11 @@
 #endif /* CONFIG_X86_64 */
 
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
-# define DISABLE_PKU		(1<<(X86_FEATURE_PKU))
-# define DISABLE_OSPKE		(1<<(X86_FEATURE_OSPKE))
-#else
 # define DISABLE_PKU		0
 # define DISABLE_OSPKE		0
+#else
+# define DISABLE_PKU		(1<<(X86_FEATURE_PKU & 31))
+# define DISABLE_OSPKE		(1<<(X86_FEATURE_OSPKE & 31))
 #endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
 
 /*

[PATCH 4.4.y 019/101] x86/cpufeature: Update cpufeaure macros

[Srivatsa S. Bhat]

From: Dave Hansen <dave.hansen@linux.intel.com>

commit 6e17cb9c2d5efd8fcc3934e983733302b9912ff8 upstream

We had a new CPUID "NCAPINT" word added, but the REQUIRED_MASK and
DISABLED_MASK macros did not get updated.  Update them.

None of the features was needed in these masks, so there was no
harm, but we should keep them updated anyway.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20160629200107.8D3C9A31@viggo.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeature.h        |    6 ++++--
 arch/x86/include/asm/disabled-features.h |    1 +
 arch/x86/include/asm/required-features.h |    1 +
 3 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index aa7785e..c7e38da 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -66,7 +66,8 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK13)) ||	\
 	   (((bit)>>5)==14 && (1UL<<((bit)&31) & REQUIRED_MASK14)) ||	\
 	   (((bit)>>5)==15 && (1UL<<((bit)&31) & REQUIRED_MASK15)) ||	\
-	   (((bit)>>5)==16 && (1UL<<((bit)&31) & REQUIRED_MASK16)) )
+	   (((bit)>>5)==16 && (1UL<<((bit)&31) & REQUIRED_MASK16)) ||	\
+	   (((bit)>>5)==17 && (1UL<<((bit)&31) & REQUIRED_MASK17)))
 
 #define DISABLED_MASK_BIT_SET(bit)					\
 	 ( (((bit)>>5)==0  && (1UL<<((bit)&31) & DISABLED_MASK0 )) ||	\
@@ -85,7 +86,8 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK13)) ||	\
 	   (((bit)>>5)==14 && (1UL<<((bit)&31) & DISABLED_MASK14)) ||	\
 	   (((bit)>>5)==15 && (1UL<<((bit)&31) & DISABLED_MASK15)) ||	\
-	   (((bit)>>5)==16 && (1UL<<((bit)&31) & DISABLED_MASK16)) )
+	   (((bit)>>5)==16 && (1UL<<((bit)&31) & DISABLED_MASK16)) ||	\
+	   (((bit)>>5)==17 && (1UL<<((bit)&31) & DISABLED_MASK17)))
 
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 0403b22..ab6b05c 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -58,5 +58,6 @@
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
 #define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE)
+#define DISABLED_MASK17	0
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index 4916144..fad4277 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -99,5 +99,6 @@
 #define REQUIRED_MASK14	0
 #define REQUIRED_MASK15	0
 #define REQUIRED_MASK16	0
+#define REQUIRED_MASK17	0
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */

[PATCH 4.4.y 020/101] x86/cpufeature: Make sure DISABLED/REQUIRED macros are updated

[Srivatsa S. Bhat]

From: Dave Hansen <dave.hansen@linux.intel.com>

commit 1e61f78baf893c7eb49f633d23ccbb420c8f808e upstream

x86 has two macros which allow us to evaluate some CPUID-based
features at compile time:

	REQUIRED_MASK_BIT_SET()
	DISABLED_MASK_BIT_SET()

They're both defined by having the compiler check the bit
argument against some constant masks of features.

But, when adding new CPUID leaves, we need to check new words
for these macros.  So make sure that those macros and the
REQUIRED_MASK* and DISABLED_MASK* get updated when necessary.

This looks kinda silly to have an open-coded value ("18" in
this case) open-coded in 5 places in the code.  But, we really do
need 5 places updated when NCAPINTS gets bumped, so now we just
force the issue.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20160629200108.92466F6F@viggo.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeature.h        |    8 ++++++--
 arch/x86/include/asm/disabled-features.h |    1 +
 arch/x86/include/asm/required-features.h |    1 +
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index c7e38da..3d5a6b5 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -67,7 +67,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   (((bit)>>5)==14 && (1UL<<((bit)&31) & REQUIRED_MASK14)) ||	\
 	   (((bit)>>5)==15 && (1UL<<((bit)&31) & REQUIRED_MASK15)) ||	\
 	   (((bit)>>5)==16 && (1UL<<((bit)&31) & REQUIRED_MASK16)) ||	\
-	   (((bit)>>5)==17 && (1UL<<((bit)&31) & REQUIRED_MASK17)))
+	   (((bit)>>5)==17 && (1UL<<((bit)&31) & REQUIRED_MASK17)) ||	\
+	   REQUIRED_MASK_CHECK					   ||	\
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 18))
 
 #define DISABLED_MASK_BIT_SET(bit)					\
 	 ( (((bit)>>5)==0  && (1UL<<((bit)&31) & DISABLED_MASK0 )) ||	\
@@ -87,7 +89,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   (((bit)>>5)==14 && (1UL<<((bit)&31) & DISABLED_MASK14)) ||	\
 	   (((bit)>>5)==15 && (1UL<<((bit)&31) & DISABLED_MASK15)) ||	\
 	   (((bit)>>5)==16 && (1UL<<((bit)&31) & DISABLED_MASK16)) ||	\
-	   (((bit)>>5)==17 && (1UL<<((bit)&31) & DISABLED_MASK17)))
+	   (((bit)>>5)==17 && (1UL<<((bit)&31) & DISABLED_MASK17)) ||	\
+	   DISABLED_MASK_CHECK					   ||	\
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 18))
 
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index ab6b05c..21c5ac1 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -59,5 +59,6 @@
 #define DISABLED_MASK15	0
 #define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE)
 #define DISABLED_MASK17	0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index fad4277..fac9a5c 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -100,5 +100,6 @@
 #define REQUIRED_MASK15	0
 #define REQUIRED_MASK16	0
 #define REQUIRED_MASK17	0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */

[PATCH 4.4.y 021/101] x86/cpufeature: Add helper macro for mask check macros

[Srivatsa S. Bhat]

From: Dave Hansen <dave.hansen@linux.intel.com>

commit 8eda072e9d7c3429a372e3635dc5851f4a42dee1 upstream

Every time we add a word to our cpu features, we need to add
something like this in two places:

	(((bit)>>5)==16 && (1UL<<((bit)&31) & REQUIRED_MASK16))

The trick is getting the "16" in this case in both places.  I've
now screwed this up twice, so as pennance, I've come up with
this patch to keep me and other poor souls from doing the same.

I also commented the logic behind the bit manipulation showcased
above.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20160629200110.1BA8949E@viggo.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeature.h |   90 +++++++++++++++++++++----------------
 1 file changed, 50 insertions(+), 40 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 3d5a6b5..dd00898 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -49,48 +49,58 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 #define test_cpu_cap(c, bit)						\
 	 test_bit(bit, (unsigned long *)((c)->x86_capability))
 
-#define REQUIRED_MASK_BIT_SET(bit)					\
-	 ( (((bit)>>5)==0  && (1UL<<((bit)&31) & REQUIRED_MASK0 )) ||	\
-	   (((bit)>>5)==1  && (1UL<<((bit)&31) & REQUIRED_MASK1 )) ||	\
-	   (((bit)>>5)==2  && (1UL<<((bit)&31) & REQUIRED_MASK2 )) ||	\
-	   (((bit)>>5)==3  && (1UL<<((bit)&31) & REQUIRED_MASK3 )) ||	\
-	   (((bit)>>5)==4  && (1UL<<((bit)&31) & REQUIRED_MASK4 )) ||	\
-	   (((bit)>>5)==5  && (1UL<<((bit)&31) & REQUIRED_MASK5 )) ||	\
-	   (((bit)>>5)==6  && (1UL<<((bit)&31) & REQUIRED_MASK6 )) ||	\
-	   (((bit)>>5)==7  && (1UL<<((bit)&31) & REQUIRED_MASK7 )) ||	\
-	   (((bit)>>5)==8  && (1UL<<((bit)&31) & REQUIRED_MASK8 )) ||	\
-	   (((bit)>>5)==9  && (1UL<<((bit)&31) & REQUIRED_MASK9 )) ||	\
-	   (((bit)>>5)==10 && (1UL<<((bit)&31) & REQUIRED_MASK10)) ||	\
-	   (((bit)>>5)==11 && (1UL<<((bit)&31) & REQUIRED_MASK11)) ||	\
-	   (((bit)>>5)==12 && (1UL<<((bit)&31) & REQUIRED_MASK12)) ||	\
-	   (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK13)) ||	\
-	   (((bit)>>5)==14 && (1UL<<((bit)&31) & REQUIRED_MASK14)) ||	\
-	   (((bit)>>5)==15 && (1UL<<((bit)&31) & REQUIRED_MASK15)) ||	\
-	   (((bit)>>5)==16 && (1UL<<((bit)&31) & REQUIRED_MASK16)) ||	\
-	   (((bit)>>5)==17 && (1UL<<((bit)&31) & REQUIRED_MASK17)) ||	\
-	   REQUIRED_MASK_CHECK					   ||	\
+/*
+ * There are 32 bits/features in each mask word.  The high bits
+ * (selected with (bit>>5) give us the word number and the low 5
+ * bits give us the bit/feature number inside the word.
+ * (1UL<<((bit)&31) gives us a mask for the feature_bit so we can
+ * see if it is set in the mask word.
+ */
+#define CHECK_BIT_IN_MASK_WORD(maskname, word, bit)	\
+	(((bit)>>5)==(word) && (1UL<<((bit)&31) & maskname##word ))
+
+#define REQUIRED_MASK_BIT_SET(feature_bit)		\
+	 ( CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  0, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  1, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  2, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  3, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  4, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  5, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  6, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  7, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  8, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  9, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 10, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 11, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 12, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 13, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 14, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) ||	\
+	   REQUIRED_MASK_CHECK					  ||	\
 	   BUILD_BUG_ON_ZERO(NCAPINTS != 18))
 
-#define DISABLED_MASK_BIT_SET(bit)					\
-	 ( (((bit)>>5)==0  && (1UL<<((bit)&31) & DISABLED_MASK0 )) ||	\
-	   (((bit)>>5)==1  && (1UL<<((bit)&31) & DISABLED_MASK1 )) ||	\
-	   (((bit)>>5)==2  && (1UL<<((bit)&31) & DISABLED_MASK2 )) ||	\
-	   (((bit)>>5)==3  && (1UL<<((bit)&31) & DISABLED_MASK3 )) ||	\
-	   (((bit)>>5)==4  && (1UL<<((bit)&31) & DISABLED_MASK4 )) ||	\
-	   (((bit)>>5)==5  && (1UL<<((bit)&31) & DISABLED_MASK5 )) ||	\
-	   (((bit)>>5)==6  && (1UL<<((bit)&31) & DISABLED_MASK6 )) ||	\
-	   (((bit)>>5)==7  && (1UL<<((bit)&31) & DISABLED_MASK7 )) ||	\
-	   (((bit)>>5)==8  && (1UL<<((bit)&31) & DISABLED_MASK8 )) ||	\
-	   (((bit)>>5)==9  && (1UL<<((bit)&31) & DISABLED_MASK9 )) ||	\
-	   (((bit)>>5)==10 && (1UL<<((bit)&31) & DISABLED_MASK10)) ||	\
-	   (((bit)>>5)==11 && (1UL<<((bit)&31) & DISABLED_MASK11)) ||	\
-	   (((bit)>>5)==12 && (1UL<<((bit)&31) & DISABLED_MASK12)) ||	\
-	   (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK13)) ||	\
-	   (((bit)>>5)==14 && (1UL<<((bit)&31) & DISABLED_MASK14)) ||	\
-	   (((bit)>>5)==15 && (1UL<<((bit)&31) & DISABLED_MASK15)) ||	\
-	   (((bit)>>5)==16 && (1UL<<((bit)&31) & DISABLED_MASK16)) ||	\
-	   (((bit)>>5)==17 && (1UL<<((bit)&31) & DISABLED_MASK17)) ||	\
-	   DISABLED_MASK_CHECK					   ||	\
+#define DISABLED_MASK_BIT_SET(feature_bit)				\
+	 ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  0, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  1, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  2, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  3, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  4, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  5, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  6, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  7, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  8, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  9, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 10, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 11, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 12, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 13, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 14, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) ||	\
+	   DISABLED_MASK_CHECK					  ||	\
 	   BUILD_BUG_ON_ZERO(NCAPINTS != 18))
 
 #define cpu_has(c, bit)							\

[PATCH 4.4.y 022/101] x86/cpu: Probe CPUID leaf 6 even when cpuid_level == 6

[Srivatsa S. Bhat]

From: Andy Lutomirski <luto@kernel.org>

commit 3df8d9208569ef0b2313e516566222d745f3b94b upstream.

A typo (or mis-merge?) resulted in leaf 6 only being probed if
cpuid_level >= 7.

Fixes: 2ccd71f1b278 ("x86/cpufeature: Move some of the scattered feature bits to x86_capability")
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Link: http://lkml.kernel.org/r/6ea30c0e9daec21e488b54761881a6dfcf3e04d0.1481825597.git.luto@kernel.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/common.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 814276d..736e284 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -686,13 +686,14 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_1_EDX] = edx;
 	}
 
+	/* Thermal and Power Management Leaf: level 0x00000006 (eax) */
+	if (c->cpuid_level >= 0x00000006)
+		c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006);
+
 	/* Additional Intel-defined flags: level 0x00000007 */
 	if (c->cpuid_level >= 0x00000007) {
 		cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx);
-
 		c->x86_capability[CPUID_7_0_EBX] = ebx;
-
-		c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006);
 		c->x86_capability[CPUID_7_ECX] = ecx;
 	}
 

[PATCH 4.4.y 023/101] x86/cpufeatures: Add CPUID_7_EDX CPUID leaf

[Srivatsa S. Bhat]

From: David Woodhouse <dwmw@amazon.co.uk>

(cherry picked from commit 95ca0ee8636059ea2800dfbac9ecac6212d6b38f)

This is a pure feature bits leaf. There are two AVX512 feature bits in it
already which were handled as scattered bits, and three more from this leaf
are going to be added for speculation control features.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Borislav Petkov <bp@suse.de>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: ak@linux.intel.com
Cc: ashok.raj@intel.com
Cc: dave.hansen@intel.com
Cc: karahmed@amazon.de
Cc: arjan@linux.intel.com
Cc: torvalds@linux-foundation.org
Cc: peterz@infradead.org
Cc: bp@alien8.de
Cc: pbonzini@redhat.com
Cc: tim.c.chen@linux.intel.com
Cc: gregkh@linux-foundation.org
Link: https://lkml.kernel.org/r/1516896855-7642-2-git-send-email-dwmw@amazon.co.uk
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeature.h        |    7 +++++--
 arch/x86/include/asm/cpufeatures.h       |    6 +++++-
 arch/x86/include/asm/disabled-features.h |    3 ++-
 arch/x86/include/asm/required-features.h |    3 ++-
 arch/x86/kernel/cpu/common.c             |    1 +
 5 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index dd00898..d72c1db 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -28,6 +28,7 @@ enum cpuid_leafs
 	CPUID_8000_000A_EDX,
 	CPUID_7_ECX,
 	CPUID_8000_0007_EBX,
+	CPUID_7_EDX,
 };
 
 #ifdef CONFIG_X86_FEATURE_NAMES
@@ -78,8 +79,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) ||	\
 	   REQUIRED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 18))
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 19))
 
 #define DISABLED_MASK_BIT_SET(feature_bit)				\
 	 ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  0, feature_bit) ||	\
@@ -100,8 +102,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) ||	\
 	   DISABLED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 18))
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 19))
 
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 205ce70..da14ca8 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -12,7 +12,7 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS	18	/* N 32-bit words worth of info */
+#define NCAPINTS	19	/* N 32-bit words worth of info */
 #define NBUGINTS	1	/* N 32-bit bug flags */
 
 /*
@@ -285,6 +285,10 @@
 #define X86_FEATURE_SUCCOR	(17*32+1) /* Uncorrectable error containment and recovery */
 #define X86_FEATURE_SMCA	(17*32+3) /* Scalable MCA */
 
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
+#define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+
 /*
  * BUG word(s)
  */
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 21c5ac1..1f8cca4 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -59,6 +59,7 @@
 #define DISABLED_MASK15	0
 #define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE)
 #define DISABLED_MASK17	0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
+#define DISABLED_MASK18	0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index fac9a5c..6847d85 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -100,6 +100,7 @@
 #define REQUIRED_MASK15	0
 #define REQUIRED_MASK16	0
 #define REQUIRED_MASK17	0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
+#define REQUIRED_MASK18	0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 736e284..ac7c526 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -695,6 +695,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx);
 		c->x86_capability[CPUID_7_0_EBX] = ebx;
 		c->x86_capability[CPUID_7_ECX] = ecx;
+		c->x86_capability[CPUID_7_EDX] = edx;
 	}
 
 	/* Extended state features: level 0x0000000d */

[PATCH 4.4.y 024/101] x86/cpufeatures: Add Intel feature bits for Speculation Control

[Srivatsa S. Bhat]

From: David Woodhouse <dwmw@amazon.co.uk>

(cherry picked from commit fc67dd70adb711a45d2ef34e12d1a8be75edde61)

Add three feature bits exposed by new microcode on Intel CPUs for
speculation control.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Borislav Petkov <bp@suse.de>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: ak@linux.intel.com
Cc: ashok.raj@intel.com
Cc: dave.hansen@intel.com
Cc: karahmed@amazon.de
Cc: arjan@linux.intel.com
Cc: torvalds@linux-foundation.org
Cc: peterz@infradead.org
Cc: bp@alien8.de
Cc: pbonzini@redhat.com
Cc: tim.c.chen@linux.intel.com
Cc: gregkh@linux-foundation.org
Link: https://lkml.kernel.org/r/1516896855-7642-3-git-send-email-dwmw@amazon.co.uk
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeatures.h |    3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index da14ca8..f50e857 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -288,6 +288,9 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_SPEC_CTRL		(18*32+26) /* Speculation Control (IBRS + IBPB) */
+#define X86_FEATURE_STIBP		(18*32+27) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
 
 /*
  * BUG word(s)

[PATCH 4.4.y 025/101] x86/cpufeatures: Add AMD feature bits for Speculation Control

[Srivatsa S. Bhat]

From: David Woodhouse <dwmw@amazon.co.uk>

(cherry picked from commit 5d10cbc91d9eb5537998b65608441b592eec65e7)

AMD exposes the PRED_CMD/SPEC_CTRL MSRs slightly differently to Intel.
See http://lkml.kernel.org/r/2b3e25cc-286d-8bd0-aeaf-9ac4aae39de8@amd.com

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: ak@linux.intel.com
Cc: ashok.raj@intel.com
Cc: dave.hansen@intel.com
Cc: karahmed@amazon.de
Cc: arjan@linux.intel.com
Cc: torvalds@linux-foundation.org
Cc: peterz@infradead.org
Cc: bp@alien8.de
Cc: pbonzini@redhat.com
Cc: tim.c.chen@linux.intel.com
Cc: gregkh@linux-foundation.org
Link: https://lkml.kernel.org/r/1516896855-7642-4-git-send-email-dwmw@amazon.co.uk
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeatures.h |    3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index f50e857..a5671b8 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -251,6 +251,9 @@
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
 #define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
+#define X86_FEATURE_AMD_PRED_CMD (13*32+12) /* Prediction Command MSR (AMD) */
+#define X86_FEATURE_AMD_SPEC_CTRL (13*32+14) /* Speculation Control MSR only (AMD) */
+#define X86_FEATURE_AMD_STIBP	(13*32+15) /* Single Thread Indirect Branch Predictors (AMD) */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
 #define X86_FEATURE_DTHERM	(14*32+ 0) /* Digital Thermal Sensor */

[PATCH 4.4.y 026/101] x86/msr: Add definitions for new speculation control MSRs

[Srivatsa S. Bhat]

From: David Woodhouse <dwmw@amazon.co.uk>

(cherry picked from commit 1e340c60d0dd3ae07b5bedc16a0469c14b9f3410)

Add MSR and bit definitions for SPEC_CTRL, PRED_CMD and ARCH_CAPABILITIES.

See Intel's 336996-Speculative-Execution-Side-Channel-Mitigations.pdf

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: ak@linux.intel.com
Cc: ashok.raj@intel.com
Cc: dave.hansen@intel.com
Cc: karahmed@amazon.de
Cc: arjan@linux.intel.com
Cc: torvalds@linux-foundation.org
Cc: peterz@infradead.org
Cc: bp@alien8.de
Cc: pbonzini@redhat.com
Cc: tim.c.chen@linux.intel.com
Cc: gregkh@linux-foundation.org
Link: https://lkml.kernel.org/r/1516896855-7642-5-git-send-email-dwmw@amazon.co.uk
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/msr-index.h |   12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index b8911ae..f4701f0 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -32,6 +32,13 @@
 #define EFER_FFXSR		(1<<_EFER_FFXSR)
 
 /* Intel MSRs. Some also available on other CPUs */
+#define MSR_IA32_SPEC_CTRL		0x00000048 /* Speculation Control */
+#define SPEC_CTRL_IBRS			(1 << 0)   /* Indirect Branch Restricted Speculation */
+#define SPEC_CTRL_STIBP			(1 << 1)   /* Single Thread Indirect Branch Predictors */
+
+#define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
+#define PRED_CMD_IBPB			(1 << 0)   /* Indirect Branch Prediction Barrier */
+
 #define MSR_IA32_PERFCTR0		0x000000c1
 #define MSR_IA32_PERFCTR1		0x000000c2
 #define MSR_FSB_FREQ			0x000000cd
@@ -45,6 +52,11 @@
 #define SNB_C3_AUTO_UNDEMOTE		(1UL << 28)
 
 #define MSR_MTRRcap			0x000000fe
+
+#define MSR_IA32_ARCH_CAPABILITIES	0x0000010a
+#define ARCH_CAP_RDCL_NO		(1 << 0)   /* Not susceptible to Meltdown */
+#define ARCH_CAP_IBRS_ALL		(1 << 1)   /* Enhanced IBRS support */
+
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
 

[PATCH 4.4.y 027/101] x86/pti: Do not enable PTI on CPUs which are not vulnerable to Meltdown

[Srivatsa S. Bhat]

From: David Woodhouse <dwmw@amazon.co.uk>

(cherry picked from commit fec9434a12f38d3aeafeb75711b71d8a1fdef621)

Also, for CPUs which don't speculate at all, don't report that they're
vulnerable to the Spectre variants either.

Leave the cpu_no_meltdown[] match table with just X86_VENDOR_AMD in it
for now, even though that could be done with a simple comparison, on the
assumption that we'll have more to add.

Based on suggestions from Dave Hansen and Alan Cox.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Borislav Petkov <bp@suse.de>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: ak@linux.intel.com
Cc: ashok.raj@intel.com
Cc: karahmed@amazon.de
Cc: arjan@linux.intel.com
Cc: torvalds@linux-foundation.org
Cc: peterz@infradead.org
Cc: bp@alien8.de
Cc: pbonzini@redhat.com
Cc: tim.c.chen@linux.intel.com
Cc: gregkh@linux-foundation.org
Link: https://lkml.kernel.org/r/1516896855-7642-6-git-send-email-dwmw@amazon.co.uk
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/common.c |   48 ++++++++++++++++++++++++++++++++++++++----
 1 file changed, 43 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index ac7c526..d6c097c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -43,6 +43,8 @@
 #include <asm/pat.h>
 #include <asm/microcode.h>
 #include <asm/microcode_intel.h>
+#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
 
 #ifdef CONFIG_X86_LOCAL_APIC
 #include <asm/uv/uv.h>
@@ -794,6 +796,41 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #endif
 }
 
+static const __initdata struct x86_cpu_id cpu_no_speculation[] = {
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_CEDARVIEW,	X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_CLOVERVIEW,	X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_LINCROFT,	X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_PENWELL,	X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_PINEVIEW,	X86_FEATURE_ANY },
+	{ X86_VENDOR_CENTAUR,	5 },
+	{ X86_VENDOR_INTEL,	5 },
+	{ X86_VENDOR_NSC,	5 },
+	{ X86_VENDOR_ANY,	4 },
+	{}
+};
+
+static const __initdata struct x86_cpu_id cpu_no_meltdown[] = {
+	{ X86_VENDOR_AMD },
+	{}
+};
+
+static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c)
+{
+	u64 ia32_cap = 0;
+
+	if (x86_match_cpu(cpu_no_meltdown))
+		return false;
+
+	if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
+		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
+
+	/* Rogue Data Cache Load? No! */
+	if (ia32_cap & ARCH_CAP_RDCL_NO)
+		return false;
+
+	return true;
+}
+
 /*
  * Do minimum CPU detection early.
  * Fields really needed: vendor, cpuid_level, family, model, mask,
@@ -840,11 +877,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
 
-	if (c->x86_vendor != X86_VENDOR_AMD)
-		setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
-
-	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
-	setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
+	if (!x86_match_cpu(cpu_no_speculation)) {
+		if (cpu_vulnerable_to_meltdown(c))
+			setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
+		setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
+		setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
+	}
 
 	fpu__init_system(c);
 

[PATCH 4.4.y 028/101] x86/cpufeature: Blacklist SPEC_CTRL/PRED_CMD on early Spectre v2 microcodes

[Srivatsa S. Bhat]

From: David Woodhouse <dwmw@amazon.co.uk>

(cherry picked from commit a5b2966364538a0e68c9fa29bc0a3a1651799035)

This doesn't refuse to load the affected microcodes; it just refuses to
use the Spectre v2 mitigation features if they're detected, by clearing
the appropriate feature bits.

The AMD CPUID bits are handled here too, because hypervisors *may* have
been exposing those bits even on Intel chips, for fine-grained control
of what's available.

It is non-trivial to use x86_match_cpu() for this table because that
doesn't handle steppings. And the approach taken in commit bd9240a18
almost made me lose my lunch.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: ak@linux.intel.com
Cc: ashok.raj@intel.com
Cc: dave.hansen@intel.com
Cc: karahmed@amazon.de
Cc: arjan@linux.intel.com
Cc: torvalds@linux-foundation.org
Cc: peterz@infradead.org
Cc: bp@alien8.de
Cc: pbonzini@redhat.com
Cc: tim.c.chen@linux.intel.com
Cc: gregkh@linux-foundation.org
Link: https://lkml.kernel.org/r/1516896855-7642-7-git-send-email-dwmw@amazon.co.uk
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/intel-family.h |    5 ++-
 arch/x86/kernel/cpu/intel.c         |   67 +++++++++++++++++++++++++++++++++++
 2 files changed, 71 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 6999f7d..12fa187 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -12,6 +12,7 @@
  */
 
 #define INTEL_FAM6_CORE_YONAH		0x0E
+
 #define INTEL_FAM6_CORE2_MEROM		0x0F
 #define INTEL_FAM6_CORE2_MEROM_L	0x16
 #define INTEL_FAM6_CORE2_PENRYN		0x17
@@ -20,6 +21,7 @@
 #define INTEL_FAM6_NEHALEM		0x1E
 #define INTEL_FAM6_NEHALEM_EP		0x1A
 #define INTEL_FAM6_NEHALEM_EX		0x2E
+
 #define INTEL_FAM6_WESTMERE		0x25
 #define INTEL_FAM6_WESTMERE2		0x1F
 #define INTEL_FAM6_WESTMERE_EP		0x2C
@@ -36,9 +38,9 @@
 #define INTEL_FAM6_HASWELL_GT3E		0x46
 
 #define INTEL_FAM6_BROADWELL_CORE	0x3D
-#define INTEL_FAM6_BROADWELL_XEON_D	0x56
 #define INTEL_FAM6_BROADWELL_GT3E	0x47
 #define INTEL_FAM6_BROADWELL_X		0x4F
+#define INTEL_FAM6_BROADWELL_XEON_D	0x56
 
 #define INTEL_FAM6_SKYLAKE_MOBILE	0x4E
 #define INTEL_FAM6_SKYLAKE_DESKTOP	0x5E
@@ -60,6 +62,7 @@
 #define INTEL_FAM6_ATOM_MERRIFIELD2	0x5A /* Annidale */
 #define INTEL_FAM6_ATOM_GOLDMONT	0x5C
 #define INTEL_FAM6_ATOM_DENVERTON	0x5F /* Goldmont Microserver */
+#define INTEL_FAM6_ATOM_GEMINI_LAKE	0x7A
 
 /* Xeon Phi */
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 9299e3b..23ba9cc 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -13,6 +13,7 @@
 #include <asm/msr.h>
 #include <asm/bugs.h>
 #include <asm/cpu.h>
+#include <asm/intel-family.h>
 
 #ifdef CONFIG_X86_64
 #include <linux/topology.h>
@@ -25,6 +26,59 @@
 #include <asm/apic.h>
 #endif
 
+/*
+ * Early microcode releases for the Spectre v2 mitigation were broken.
+ * Information taken from;
+ * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/01/microcode-update-guidance.pdf
+ * - https://kb.vmware.com/s/article/52345
+ * - Microcode revisions observed in the wild
+ * - Release note from 20180108 microcode release
+ */
+struct sku_microcode {
+	u8 model;
+	u8 stepping;
+	u32 microcode;
+};
+static const struct sku_microcode spectre_bad_microcodes[] = {
+	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0B,	0x84 },
+	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0A,	0x84 },
+	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x09,	0x84 },
+	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x0A,	0x84 },
+	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x09,	0x84 },
+	{ INTEL_FAM6_SKYLAKE_X,		0x03,	0x0100013e },
+	{ INTEL_FAM6_SKYLAKE_X,		0x04,	0x0200003c },
+	{ INTEL_FAM6_SKYLAKE_MOBILE,	0x03,	0xc2 },
+	{ INTEL_FAM6_SKYLAKE_DESKTOP,	0x03,	0xc2 },
+	{ INTEL_FAM6_BROADWELL_CORE,	0x04,	0x28 },
+	{ INTEL_FAM6_BROADWELL_GT3E,	0x01,	0x1b },
+	{ INTEL_FAM6_BROADWELL_XEON_D,	0x02,	0x14 },
+	{ INTEL_FAM6_BROADWELL_XEON_D,	0x03,	0x07000011 },
+	{ INTEL_FAM6_BROADWELL_X,	0x01,	0x0b000025 },
+	{ INTEL_FAM6_HASWELL_ULT,	0x01,	0x21 },
+	{ INTEL_FAM6_HASWELL_GT3E,	0x01,	0x18 },
+	{ INTEL_FAM6_HASWELL_CORE,	0x03,	0x23 },
+	{ INTEL_FAM6_HASWELL_X,		0x02,	0x3b },
+	{ INTEL_FAM6_HASWELL_X,		0x04,	0x10 },
+	{ INTEL_FAM6_IVYBRIDGE_X,	0x04,	0x42a },
+	/* Updated in the 20180108 release; blacklist until we know otherwise */
+	{ INTEL_FAM6_ATOM_GEMINI_LAKE,	0x01,	0x22 },
+	/* Observed in the wild */
+	{ INTEL_FAM6_SANDYBRIDGE_X,	0x06,	0x61b },
+	{ INTEL_FAM6_SANDYBRIDGE_X,	0x07,	0x712 },
+};
+
+static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) {
+		if (c->x86_model == spectre_bad_microcodes[i].model &&
+		    c->x86_mask == spectre_bad_microcodes[i].stepping)
+			return (c->microcode <= spectre_bad_microcodes[i].microcode);
+	}
+	return false;
+}
+
 static void early_init_intel(struct cpuinfo_x86 *c)
 {
 	u64 misc_enable;
@@ -51,6 +105,19 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode);
 	}
 
+	if ((cpu_has(c, X86_FEATURE_SPEC_CTRL) ||
+	     cpu_has(c, X86_FEATURE_STIBP) ||
+	     cpu_has(c, X86_FEATURE_AMD_SPEC_CTRL) ||
+	     cpu_has(c, X86_FEATURE_AMD_PRED_CMD) ||
+	     cpu_has(c, X86_FEATURE_AMD_STIBP)) && bad_spectre_microcode(c)) {
+		pr_warn("Intel Spectre v2 broken microcode detected; disabling SPEC_CTRL\n");
+		clear_cpu_cap(c, X86_FEATURE_SPEC_CTRL);
+		clear_cpu_cap(c, X86_FEATURE_STIBP);
+		clear_cpu_cap(c, X86_FEATURE_AMD_SPEC_CTRL);
+		clear_cpu_cap(c, X86_FEATURE_AMD_PRED_CMD);
+		clear_cpu_cap(c, X86_FEATURE_AMD_STIBP);
+	}
+
 	/*
 	 * Atom erratum AAE44/AAF40/AAG38/AAH41:
 	 *

[PATCH 4.4.y 029/101] x86/speculation: Add basic IBPB (Indirect Branch Prediction Barrier) support

[Srivatsa S. Bhat]

From: David Woodhouse <dwmw@amazon.co.uk>

(cherry picked from commit 20ffa1caecca4db8f79fe665acdeaa5af815a24d)

Expose indirect_branch_prediction_barrier() for use in subsequent patches.

[ tglx: Add IBPB status to spectre_v2 sysfs file ]

Co-developed-by: KarimAllah Ahmed <karahmed@amazon.de>
Signed-off-by: KarimAllah Ahmed <karahmed@amazon.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: ak@linux.intel.com
Cc: ashok.raj@intel.com
Cc: dave.hansen@intel.com
Cc: arjan@linux.intel.com
Cc: torvalds@linux-foundation.org
Cc: peterz@infradead.org
Cc: bp@alien8.de
Cc: pbonzini@redhat.com
Cc: tim.c.chen@linux.intel.com
Cc: gregkh@linux-foundation.org
Link: https://lkml.kernel.org/r/1516896855-7642-8-git-send-email-dwmw@amazon.co.uk
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeatures.h   |    2 ++
 arch/x86/include/asm/nospec-branch.h |   13 +++++++++++++
 arch/x86/kernel/cpu/bugs.c           |   10 +++++++++-
 3 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index a5671b8..b4e370b 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -201,6 +201,8 @@
 /* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */
 #define X86_FEATURE_KAISER	( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */
 
+#define X86_FEATURE_IBPB		( 7*32+21) /* Indirect Branch Prediction Barrier enabled*/
+
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
 #define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 8b91041..41851af 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -194,6 +194,19 @@ static inline void vmexit_fill_RSB(void)
 #endif
 }
 
+static inline void indirect_branch_prediction_barrier(void)
+{
+	asm volatile(ALTERNATIVE("",
+				 "movl %[msr], %%ecx\n\t"
+				 "movl %[val], %%eax\n\t"
+				 "movl $0, %%edx\n\t"
+				 "wrmsr",
+				 X86_FEATURE_IBPB)
+		     : : [msr] "i" (MSR_IA32_PRED_CMD),
+			 [val] "i" (PRED_CMD_IBPB)
+		     : "eax", "ecx", "edx", "memory");
+}
+
 #endif /* __ASSEMBLY__ */
 
 /*
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 2bbc74f..7def33a 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -296,6 +296,13 @@ retpoline_auto:
 		setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
 		pr_info("Filling RSB on context switch\n");
 	}
+
+	/* Initialize Indirect Branch Prediction Barrier if supported */
+	if (boot_cpu_has(X86_FEATURE_SPEC_CTRL) ||
+	    boot_cpu_has(X86_FEATURE_AMD_PRED_CMD)) {
+		setup_force_cpu_cap(X86_FEATURE_IBPB);
+		pr_info("Enabling Indirect Branch Prediction Barrier\n");
+	}
 }
 
 #undef pr_fmt
@@ -325,7 +332,8 @@ ssize_t cpu_show_spectre_v2(struct device *dev,
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
 		return sprintf(buf, "Not affected\n");
 
-	return sprintf(buf, "%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+	return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+		       boot_cpu_has(X86_FEATURE_IBPB) ? ", IBPB" : "",
 		       spectre_v2_module_string());
 }
 #endif

[PATCH 4.4.y 030/101] x86/cpufeatures: Clean up Spectre v2 related CPUID flags

[Srivatsa S. Bhat]

From: David Woodhouse <dwmw@amazon.co.uk>

(cherry picked from commit 2961298efe1ea1b6fc0d7ee8b76018fa6c0bcef2)

We want to expose the hardware features simply in /proc/cpuinfo as "ibrs",
"ibpb" and "stibp". Since AMD has separate CPUID bits for those, use them
as the user-visible bits.

When the Intel SPEC_CTRL bit is set which indicates both IBRS and IBPB
capability, set those (AMD) bits accordingly. Likewise if the Intel STIBP
bit is set, set the AMD STIBP that's used for the generic hardware
capability.

Hide the rest from /proc/cpuinfo by putting "" in the comments. Including
RETPOLINE and RETPOLINE_AMD which shouldn't be visible there. There are
patches to make the sysfs vulnerabilities information non-readable by
non-root, and the same should apply to all information about which
mitigations are actually in use. Those *shouldn't* appear in /proc/cpuinfo.

The feature bit for whether IBPB is actually used, which is needed for
ALTERNATIVEs, is renamed to X86_FEATURE_USE_IBPB.

Originally-by: Borislav Petkov <bp@suse.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: ak@linux.intel.com
Cc: dave.hansen@intel.com
Cc: karahmed@amazon.de
Cc: arjan@linux.intel.com
Cc: torvalds@linux-foundation.org
Cc: peterz@infradead.org
Cc: bp@alien8.de
Cc: pbonzini@redhat.com
Cc: tim.c.chen@linux.intel.com
Cc: gregkh@linux-foundation.org
Link: https://lkml.kernel.org/r/1517070274-12128-2-git-send-email-dwmw@amazon.co.uk
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeatures.h   |   18 +++++++++---------
 arch/x86/include/asm/nospec-branch.h |    2 +-
 arch/x86/kernel/cpu/bugs.c           |    7 +++----
 arch/x86/kernel/cpu/intel.c          |   31 +++++++++++++++++++++----------
 4 files changed, 34 insertions(+), 24 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index b4e370b..782005d 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -194,14 +194,14 @@
 #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
 
 #define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
-#define X86_FEATURE_RSB_CTXSW	( 7*32+19) /* Fill RSB on context switches */
+#define X86_FEATURE_RSB_CTXSW	( 7*32+19) /* "" Fill RSB on context switches */
 
-#define X86_FEATURE_RETPOLINE	( 7*32+29) /* Generic Retpoline mitigation for Spectre variant 2 */
-#define X86_FEATURE_RETPOLINE_AMD ( 7*32+30) /* AMD Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE	( 7*32+29) /* "" Generic Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_AMD ( 7*32+30) /* "" AMD Retpoline mitigation for Spectre variant 2 */
 /* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */
 #define X86_FEATURE_KAISER	( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */
 
-#define X86_FEATURE_IBPB		( 7*32+21) /* Indirect Branch Prediction Barrier enabled*/
+#define X86_FEATURE_USE_IBPB	( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled*/
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
@@ -253,9 +253,9 @@
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
 #define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
-#define X86_FEATURE_AMD_PRED_CMD (13*32+12) /* Prediction Command MSR (AMD) */
-#define X86_FEATURE_AMD_SPEC_CTRL (13*32+14) /* Speculation Control MSR only (AMD) */
-#define X86_FEATURE_AMD_STIBP	(13*32+15) /* Single Thread Indirect Branch Predictors (AMD) */
+#define X86_FEATURE_IBPB	(13*32+12) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_IBRS	(13*32+14) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_STIBP	(13*32+15) /* Single Thread Indirect Branch Predictors */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
 #define X86_FEATURE_DTHERM	(14*32+ 0) /* Digital Thermal Sensor */
@@ -293,8 +293,8 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
-#define X86_FEATURE_SPEC_CTRL		(18*32+26) /* Speculation Control (IBRS + IBPB) */
-#define X86_FEATURE_STIBP		(18*32+27) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
+#define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
 
 /*
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 41851af..8dcecb9 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -201,7 +201,7 @@ static inline void indirect_branch_prediction_barrier(void)
 				 "movl %[val], %%eax\n\t"
 				 "movl $0, %%edx\n\t"
 				 "wrmsr",
-				 X86_FEATURE_IBPB)
+				 X86_FEATURE_USE_IBPB)
 		     : : [msr] "i" (MSR_IA32_PRED_CMD),
 			 [val] "i" (PRED_CMD_IBPB)
 		     : "eax", "ecx", "edx", "memory");
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 7def33a..1968baf 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -298,9 +298,8 @@ retpoline_auto:
 	}
 
 	/* Initialize Indirect Branch Prediction Barrier if supported */
-	if (boot_cpu_has(X86_FEATURE_SPEC_CTRL) ||
-	    boot_cpu_has(X86_FEATURE_AMD_PRED_CMD)) {
-		setup_force_cpu_cap(X86_FEATURE_IBPB);
+	if (boot_cpu_has(X86_FEATURE_IBPB)) {
+		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
 		pr_info("Enabling Indirect Branch Prediction Barrier\n");
 	}
 }
@@ -333,7 +332,7 @@ ssize_t cpu_show_spectre_v2(struct device *dev,
 		return sprintf(buf, "Not affected\n");
 
 	return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
-		       boot_cpu_has(X86_FEATURE_IBPB) ? ", IBPB" : "",
+		       boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
 		       spectre_v2_module_string());
 }
 #endif
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 23ba9cc..fee94ee 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -105,17 +105,28 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode);
 	}
 
-	if ((cpu_has(c, X86_FEATURE_SPEC_CTRL) ||
-	     cpu_has(c, X86_FEATURE_STIBP) ||
-	     cpu_has(c, X86_FEATURE_AMD_SPEC_CTRL) ||
-	     cpu_has(c, X86_FEATURE_AMD_PRED_CMD) ||
-	     cpu_has(c, X86_FEATURE_AMD_STIBP)) && bad_spectre_microcode(c)) {
-		pr_warn("Intel Spectre v2 broken microcode detected; disabling SPEC_CTRL\n");
-		clear_cpu_cap(c, X86_FEATURE_SPEC_CTRL);
+	/*
+	 * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support,
+	 * and they also have a different bit for STIBP support. Also,
+	 * a hypervisor might have set the individual AMD bits even on
+	 * Intel CPUs, for finer-grained selection of what's available.
+	 */
+	if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) {
+		set_cpu_cap(c, X86_FEATURE_IBRS);
+		set_cpu_cap(c, X86_FEATURE_IBPB);
+	}
+	if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
+		set_cpu_cap(c, X86_FEATURE_STIBP);
+
+	/* Now if any of them are set, check the blacklist and clear the lot */
+	if ((cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) ||
+	     cpu_has(c, X86_FEATURE_STIBP)) && bad_spectre_microcode(c)) {
+		pr_warn("Intel Spectre v2 broken microcode detected; disabling Speculation Control\n");
+		clear_cpu_cap(c, X86_FEATURE_IBRS);
+		clear_cpu_cap(c, X86_FEATURE_IBPB);
 		clear_cpu_cap(c, X86_FEATURE_STIBP);
-		clear_cpu_cap(c, X86_FEATURE_AMD_SPEC_CTRL);
-		clear_cpu_cap(c, X86_FEATURE_AMD_PRED_CMD);
-		clear_cpu_cap(c, X86_FEATURE_AMD_STIBP);
+		clear_cpu_cap(c, X86_FEATURE_SPEC_CTRL);
+		clear_cpu_cap(c, X86_FEATURE_INTEL_STIBP);
 	}
 
 	/*

[PATCH 4.4.y 031/101] x86/cpuid: Fix up "virtual" IBRS/IBPB/STIBP feature bits on Intel

[Srivatsa S. Bhat]

From: David Woodhouse <dwmw@amazon.co.uk>

(cherry picked from commit 7fcae1118f5fd44a862aa5c3525248e35ee67c3b)

Despite the fact that all the other code there seems to be doing it, just
using set_cpu_cap() in early_intel_init() doesn't actually work.

For CPUs with PKU support, setup_pku() calls get_cpu_cap() after
c->c_init() has set those feature bits. That resets those bits back to what
was queried from the hardware.

Turning the bits off for bad microcode is easy to fix. That can just use
setup_clear_cpu_cap() to force them off for all CPUs.

I was less keen on forcing the feature bits *on* that way, just in case
of inconsistencies. I appreciate that the kernel is going to get this
utterly wrong if CPU features are not consistent, because it has already
applied alternatives by the time secondary CPUs are brought up.

But at least if setup_force_cpu_cap() isn't being used, we might have a
chance of *detecting* the lack of the corresponding bit and either
panicking or refusing to bring the offending CPU online.

So ensure that the appropriate feature bits are set within get_cpu_cap()
regardless of how many extra times it's called.

Fixes: 2961298e ("x86/cpufeatures: Clean up Spectre v2 related CPUID flags")
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: karahmed@amazon.de
Cc: peterz@infradead.org
Cc: bp@alien8.de
Link: https://lkml.kernel.org/r/1517322623-15261-1-git-send-email-dwmw@amazon.co.uk
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/common.c |   21 +++++++++++++++++++++
 arch/x86/kernel/cpu/intel.c  |   27 ++++++++-------------------
 2 files changed, 29 insertions(+), 19 deletions(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index d6c097c..72d7e5a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -676,6 +676,26 @@ static void apply_forced_caps(struct cpuinfo_x86 *c)
 	}
 }
 
+static void init_speculation_control(struct cpuinfo_x86 *c)
+{
+	/*
+	 * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support,
+	 * and they also have a different bit for STIBP support. Also,
+	 * a hypervisor might have set the individual AMD bits even on
+	 * Intel CPUs, for finer-grained selection of what's available.
+	 *
+	 * We use the AMD bits in 0x8000_0008 EBX as the generic hardware
+	 * features, which are visible in /proc/cpuinfo and used by the
+	 * kernel. So set those accordingly from the Intel bits.
+	 */
+	if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) {
+		set_cpu_cap(c, X86_FEATURE_IBRS);
+		set_cpu_cap(c, X86_FEATURE_IBPB);
+	}
+	if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
+		set_cpu_cap(c, X86_FEATURE_STIBP);
+}
+
 void get_cpu_cap(struct cpuinfo_x86 *c)
 {
 	u32 eax, ebx, ecx, edx;
@@ -768,6 +788,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
 
 	init_scattered_cpuid_features(c);
+	init_speculation_control(c);
 }
 
 static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index fee94ee..0f13189 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -105,28 +105,17 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode);
 	}
 
-	/*
-	 * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support,
-	 * and they also have a different bit for STIBP support. Also,
-	 * a hypervisor might have set the individual AMD bits even on
-	 * Intel CPUs, for finer-grained selection of what's available.
-	 */
-	if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) {
-		set_cpu_cap(c, X86_FEATURE_IBRS);
-		set_cpu_cap(c, X86_FEATURE_IBPB);
-	}
-	if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
-		set_cpu_cap(c, X86_FEATURE_STIBP);
-
 	/* Now if any of them are set, check the blacklist and clear the lot */
-	if ((cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) ||
+	if ((cpu_has(c, X86_FEATURE_SPEC_CTRL) ||
+	     cpu_has(c, X86_FEATURE_INTEL_STIBP) ||
+	     cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) ||
 	     cpu_has(c, X86_FEATURE_STIBP)) && bad_spectre_microcode(c)) {
 		pr_warn("Intel Spectre v2 broken microcode detected; disabling Speculation Control\n");
-		clear_cpu_cap(c, X86_FEATURE_IBRS);
-		clear_cpu_cap(c, X86_FEATURE_IBPB);
-		clear_cpu_cap(c, X86_FEATURE_STIBP);
-		clear_cpu_cap(c, X86_FEATURE_SPEC_CTRL);
-		clear_cpu_cap(c, X86_FEATURE_INTEL_STIBP);
+		setup_clear_cpu_cap(X86_FEATURE_IBRS);
+		setup_clear_cpu_cap(X86_FEATURE_IBPB);
+		setup_clear_cpu_cap(X86_FEATURE_STIBP);
+		setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL);
+		setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP);
 	}
 
 	/*

[PATCH 4.4.y 032/101] x86/pti: Mark constant arrays as __initconst

[Srivatsa S. Bhat]

From: Arnd Bergmann <arnd@arndb.de>

(cherry picked from commit 4bf5d56d429cbc96c23d809a08f63cd29e1a702e)

I'm seeing build failures from the two newly introduced arrays that
are marked 'const' and '__initdata', which are mutually exclusive:

arch/x86/kernel/cpu/common.c:882:43: error: 'cpu_no_speculation' causes a section type conflict with 'e820_table_firmware_init'
arch/x86/kernel/cpu/common.c:895:43: error: 'cpu_no_meltdown' causes a section type conflict with 'e820_table_firmware_init'

The correct annotation is __initconst.

Fixes: fec9434a12f3 ("x86/pti: Do not enable PTI on CPUs which are not vulnerable to Meltdown")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@suse.de>
Cc: Thomas Garnier <thgarnie@google.com>
Cc: David Woodhouse <dwmw@amazon.co.uk>
Link: https://lkml.kernel.org/r/20180202213959.611210-1-arnd@arndb.de
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/common.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 72d7e5a..48499b4 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -817,7 +817,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #endif
 }
 
-static const __initdata struct x86_cpu_id cpu_no_speculation[] = {
+static const __initconst struct x86_cpu_id cpu_no_speculation[] = {
 	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_CEDARVIEW,	X86_FEATURE_ANY },
 	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_CLOVERVIEW,	X86_FEATURE_ANY },
 	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_LINCROFT,	X86_FEATURE_ANY },
@@ -830,7 +830,7 @@ static const __initdata struct x86_cpu_id cpu_no_speculation[] = {
 	{}
 };
 
-static const __initdata struct x86_cpu_id cpu_no_meltdown[] = {
+static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
 	{ X86_VENDOR_AMD },
 	{}
 };

[PATCH 4.4.y 033/101] x86/asm/entry/32: Simplify pushes of zeroed pt_regs->REGs

[Srivatsa S. Bhat]

From: Denys Vlasenko <dvlasenk@redhat.com>

commit 778843f934e362ed4ed734520f60a44a78a074b4 upstream

Use of a temporary R8 register here seems to be unnecessary.

"push %r8" is a two-byte insn (it needs REX prefix to specify R8),
"push $0" is two-byte too. It seems just using the latter would be
no worse.

Thus, code had an unnecessary "xorq %r8,%r8" insn.
It probably costs nothing in execution time here since we are probably
limited by store bandwidth at this point, but still.

Run-tested under QEMU: 32-bit calls still work:

 / # ./test_syscall_vdso32
 [RUN]	Executing 6-argument 32-bit syscall via VDSO
 [OK]	Arguments are preserved across syscall
 [NOTE]	R11 has changed:0000000000200ed7 - assuming clobbered by SYSRET insn
 [OK]	R8..R15 did not leak kernel data
 [RUN]	Executing 6-argument 32-bit syscall via INT 80
 [OK]	Arguments are preserved across syscall
 [OK]	R8..R15 did not leak kernel data
 [RUN]	Running tests under ptrace
 [RUN]	Executing 6-argument 32-bit syscall via VDSO
 [OK]	Arguments are preserved across syscall
 [NOTE]	R11 has changed:0000000000200ed7 - assuming clobbered by SYSRET insn
 [OK]	R8..R15 did not leak kernel data
 [RUN]	Executing 6-argument 32-bit syscall via INT 80
 [OK]	Arguments are preserved across syscall
 [OK]	R8..R15 did not leak kernel data

Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
Acked-by: Andy Lutomirski <luto@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Drewry <wad@chromium.org>
Cc: linux-kernel@vger.kernel.org
Link: http://lkml.kernel.org/r/1462201010-16846-1-git-send-email-dvlasenk@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/entry/entry_64_compat.S |   45 ++++++++++++++++++--------------------
 1 file changed, 21 insertions(+), 24 deletions(-)

diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index d03bf0e..e479ff8 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -79,24 +79,23 @@ ENTRY(entry_SYSENTER_compat)
 	ASM_CLAC			/* Clear AC after saving FLAGS */
 
 	pushq	$__USER32_CS		/* pt_regs->cs */
-	xorq    %r8,%r8
-	pushq	%r8			/* pt_regs->ip = 0 (placeholder) */
+	pushq	$0			/* pt_regs->ip = 0 (placeholder) */
 	pushq	%rax			/* pt_regs->orig_ax */
 	pushq	%rdi			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
 	pushq	%rdx			/* pt_regs->dx */
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
-	pushq   %r8                     /* pt_regs->r8  = 0 */
-	pushq   %r8                     /* pt_regs->r9  = 0 */
-	pushq   %r8                     /* pt_regs->r10 = 0 */
-	pushq   %r8                     /* pt_regs->r11 = 0 */
+	pushq   $0			/* pt_regs->r8  = 0 */
+	pushq   $0			/* pt_regs->r9  = 0 */
+	pushq   $0			/* pt_regs->r10 = 0 */
+	pushq   $0			/* pt_regs->r11 = 0 */
 	pushq   %rbx                    /* pt_regs->rbx */
 	pushq   %rbp                    /* pt_regs->rbp (will be overwritten) */
-	pushq   %r8                     /* pt_regs->r12 = 0 */
-	pushq   %r8                     /* pt_regs->r13 = 0 */
-	pushq   %r8                     /* pt_regs->r14 = 0 */
-	pushq   %r8                     /* pt_regs->r15 = 0 */
+	pushq   $0			/* pt_regs->r12 = 0 */
+	pushq   $0			/* pt_regs->r13 = 0 */
+	pushq   $0			/* pt_regs->r14 = 0 */
+	pushq   $0			/* pt_regs->r15 = 0 */
 	cld
 
 	/*
@@ -185,17 +184,16 @@ ENTRY(entry_SYSCALL_compat)
 	pushq	%rdx			/* pt_regs->dx */
 	pushq	%rbp			/* pt_regs->cx (stashed in bp) */
 	pushq	$-ENOSYS		/* pt_regs->ax */
-	xorq    %r8,%r8
-	pushq   %r8                     /* pt_regs->r8  = 0 */
-	pushq   %r8                     /* pt_regs->r9  = 0 */
-	pushq   %r8                     /* pt_regs->r10 = 0 */
-	pushq   %r8                     /* pt_regs->r11 = 0 */
+	pushq   $0			/* pt_regs->r8  = 0 */
+	pushq   $0			/* pt_regs->r9  = 0 */
+	pushq   $0			/* pt_regs->r10 = 0 */
+	pushq   $0			/* pt_regs->r11 = 0 */
 	pushq   %rbx                    /* pt_regs->rbx */
 	pushq   %rbp                    /* pt_regs->rbp (will be overwritten) */
-	pushq   %r8                     /* pt_regs->r12 = 0 */
-	pushq   %r8                     /* pt_regs->r13 = 0 */
-	pushq   %r8                     /* pt_regs->r14 = 0 */
-	pushq   %r8                     /* pt_regs->r15 = 0 */
+	pushq   $0			/* pt_regs->r12 = 0 */
+	pushq   $0			/* pt_regs->r13 = 0 */
+	pushq   $0			/* pt_regs->r14 = 0 */
+	pushq   $0			/* pt_regs->r15 = 0 */
 
 	/*
 	 * User mode is traced as though IRQs are on, and SYSENTER
@@ -292,11 +290,10 @@ ENTRY(entry_INT80_compat)
 	pushq	%rdx			/* pt_regs->dx */
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
-	xorq    %r8,%r8
-	pushq   %r8                     /* pt_regs->r8  = 0 */
-	pushq   %r8                     /* pt_regs->r9  = 0 */
-	pushq   %r8                     /* pt_regs->r10 = 0 */
-	pushq   %r8                     /* pt_regs->r11 = 0 */
+	pushq   $0			/* pt_regs->r8  = 0 */
+	pushq   $0			/* pt_regs->r9  = 0 */
+	pushq   $0			/* pt_regs->r10 = 0 */
+	pushq   $0			/* pt_regs->r11 = 0 */
 	pushq   %rbx                    /* pt_regs->rbx */
 	pushq   %rbp                    /* pt_regs->rbp */
 	pushq   %r12                    /* pt_regs->r12 */

[PATCH 4.4.y 034/101] x86/entry/64/compat: Clear registers for compat syscalls, to reduce speculation attack surface

[Srivatsa S. Bhat]

From: Dan Williams <dan.j.williams@intel.com>

commit 6b8cf5cc9965673951f1ab3f0e3cf23d06e3e2ee upstream.

At entry userspace may have populated registers with values that could
otherwise be useful in a speculative execution attack. Clear them to
minimize the kernel's attack surface.

Originally-From: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Cc: <stable@vger.kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/151787989697.7847.4083702787288600552.stgit@dwillia2-desk3.amr.corp.intel.com
[ Made small improvements to the changelog. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/entry/entry_64_compat.S |   30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index e479ff8..48c27c3 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -87,15 +87,25 @@ ENTRY(entry_SYSENTER_compat)
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	pushq   $0			/* pt_regs->r8  = 0 */
+	xorq	%r8, %r8		/* nospec   r8 */
 	pushq   $0			/* pt_regs->r9  = 0 */
+	xorq	%r9, %r9		/* nospec   r9 */
 	pushq   $0			/* pt_regs->r10 = 0 */
+	xorq	%r10, %r10		/* nospec   r10 */
 	pushq   $0			/* pt_regs->r11 = 0 */
+	xorq	%r11, %r11		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
+	xorl	%ebx, %ebx		/* nospec   rbx */
 	pushq   %rbp                    /* pt_regs->rbp (will be overwritten) */
+	xorl	%ebp, %ebp		/* nospec   rbp */
 	pushq   $0			/* pt_regs->r12 = 0 */
+	xorq	%r12, %r12		/* nospec   r12 */
 	pushq   $0			/* pt_regs->r13 = 0 */
+	xorq	%r13, %r13		/* nospec   r13 */
 	pushq   $0			/* pt_regs->r14 = 0 */
+	xorq	%r14, %r14		/* nospec   r14 */
 	pushq   $0			/* pt_regs->r15 = 0 */
+	xorq	%r15, %r15		/* nospec   r15 */
 	cld
 
 	/*
@@ -185,15 +195,25 @@ ENTRY(entry_SYSCALL_compat)
 	pushq	%rbp			/* pt_regs->cx (stashed in bp) */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	pushq   $0			/* pt_regs->r8  = 0 */
+	xorq	%r8, %r8		/* nospec   r8 */
 	pushq   $0			/* pt_regs->r9  = 0 */
+	xorq	%r9, %r9		/* nospec   r9 */
 	pushq   $0			/* pt_regs->r10 = 0 */
+	xorq	%r10, %r10		/* nospec   r10 */
 	pushq   $0			/* pt_regs->r11 = 0 */
+	xorq	%r11, %r11		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
+	xorl	%ebx, %ebx		/* nospec   rbx */
 	pushq   %rbp                    /* pt_regs->rbp (will be overwritten) */
+	xorl	%ebp, %ebp		/* nospec   rbp */
 	pushq   $0			/* pt_regs->r12 = 0 */
+	xorq	%r12, %r12		/* nospec   r12 */
 	pushq   $0			/* pt_regs->r13 = 0 */
+	xorq	%r13, %r13		/* nospec   r13 */
 	pushq   $0			/* pt_regs->r14 = 0 */
+	xorq	%r14, %r14		/* nospec   r14 */
 	pushq   $0			/* pt_regs->r15 = 0 */
+	xorq	%r15, %r15		/* nospec   r15 */
 
 	/*
 	 * User mode is traced as though IRQs are on, and SYSENTER
@@ -291,15 +311,25 @@ ENTRY(entry_INT80_compat)
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	pushq   $0			/* pt_regs->r8  = 0 */
+	xorq	%r8, %r8		/* nospec   r8 */
 	pushq   $0			/* pt_regs->r9  = 0 */
+	xorq	%r9, %r9		/* nospec   r9 */
 	pushq   $0			/* pt_regs->r10 = 0 */
+	xorq	%r10, %r10		/* nospec   r10 */
 	pushq   $0			/* pt_regs->r11 = 0 */
+	xorq	%r11, %r11		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
+	xorl	%ebx, %ebx		/* nospec   rbx */
 	pushq   %rbp                    /* pt_regs->rbp */
+	xorl	%ebp, %ebp		/* nospec   rbp */
 	pushq   %r12                    /* pt_regs->r12 */
+	xorq	%r12, %r12		/* nospec   r12 */
 	pushq   %r13                    /* pt_regs->r13 */
+	xorq	%r13, %r13		/* nospec   r13 */
 	pushq   %r14                    /* pt_regs->r14 */
+	xorq	%r14, %r14		/* nospec   r14 */
 	pushq   %r15                    /* pt_regs->r15 */
+	xorq	%r15, %r15		/* nospec   r15 */
 	cld
 
 	/*

[PATCH 4.4.y 035/101] x86/speculation: Update Speculation Control microcode blacklist

[Srivatsa S. Bhat]

From: David Woodhouse <dwmw@amazon.co.uk>

commit 1751342095f0d2b36fa8114d8e12c5688c455ac4 upstream.

Intel have retroactively blessed the 0xc2 microcode on Skylake mobile
and desktop parts, and the Gemini Lake 0x22 microcode is apparently fine
too. We blacklisted the latter purely because it was present with all
the other problematic ones in the 2018-01-08 release, but now it's
explicitly listed as OK.

We still list 0x84 for the various Kaby Lake / Coffee Lake parts, as
that appeared in one version of the blacklist and then reverted to
0x80 again. We can change it if 0x84 is actually announced to be safe.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: arjan.van.de.ven@intel.com
Cc: jmattson@google.com
Cc: karahmed@amazon.de
Cc: kvm@vger.kernel.org
Cc: pbonzini@redhat.com
Cc: rkrcmar@redhat.com
Cc: sironi@amazon.de
Link: http://lkml.kernel.org/r/1518305967-31356-2-git-send-email-dwmw@amazon.co.uk
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/intel.c |    4 ----
 1 file changed, 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 0f13189..71492d2 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -47,8 +47,6 @@ static const struct sku_microcode spectre_bad_microcodes[] = {
 	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x09,	0x84 },
 	{ INTEL_FAM6_SKYLAKE_X,		0x03,	0x0100013e },
 	{ INTEL_FAM6_SKYLAKE_X,		0x04,	0x0200003c },
-	{ INTEL_FAM6_SKYLAKE_MOBILE,	0x03,	0xc2 },
-	{ INTEL_FAM6_SKYLAKE_DESKTOP,	0x03,	0xc2 },
 	{ INTEL_FAM6_BROADWELL_CORE,	0x04,	0x28 },
 	{ INTEL_FAM6_BROADWELL_GT3E,	0x01,	0x1b },
 	{ INTEL_FAM6_BROADWELL_XEON_D,	0x02,	0x14 },
@@ -60,8 +58,6 @@ static const struct sku_microcode spectre_bad_microcodes[] = {
 	{ INTEL_FAM6_HASWELL_X,		0x02,	0x3b },
 	{ INTEL_FAM6_HASWELL_X,		0x04,	0x10 },
 	{ INTEL_FAM6_IVYBRIDGE_X,	0x04,	0x42a },
-	/* Updated in the 20180108 release; blacklist until we know otherwise */
-	{ INTEL_FAM6_ATOM_GEMINI_LAKE,	0x01,	0x22 },
 	/* Observed in the wild */
 	{ INTEL_FAM6_SANDYBRIDGE_X,	0x06,	0x61b },
 	{ INTEL_FAM6_SANDYBRIDGE_X,	0x07,	0x712 },

[PATCH 4.4.y 036/101] x86/speculation: Correct Speculation Control microcode blacklist again

[Srivatsa S. Bhat]

From: David Woodhouse <dwmw@amazon.co.uk>

commit d37fc6d360a404b208547ba112e7dabb6533c7fc upstream.

Arjan points out that the Intel document only clears the 0xc2 microcode
on *some* parts with CPUID 506E3 (INTEL_FAM6_SKYLAKE_DESKTOP stepping 3).
For the Skylake H/S platform it's OK but for Skylake E3 which has the
same CPUID it isn't (yet) cleared.

So removing it from the blacklist was premature. Put it back for now.

Also, Arjan assures me that the 0x84 microcode for Kaby Lake which was
featured in one of the early revisions of the Intel document was never
released to the public, and won't be until/unless it is also validated
as safe. So those can change to 0x80 which is what all *other* versions
of the doc have identified.

Once the retrospective testing of existing public microcodes is done, we
should be back into a mode where new microcodes are only released in
batches and we shouldn't even need to update the blacklist for those
anyway, so this tweaking of the list isn't expected to be a thing which
keeps happening.

Requested-by: Arjan van de Ven <arjan.van.de.ven@intel.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: arjan.van.de.ven@intel.com
Cc: dave.hansen@intel.com
Cc: kvm@vger.kernel.org
Cc: pbonzini@redhat.com
Link: http://lkml.kernel.org/r/1518449255-2182-1-git-send-email-dwmw@amazon.co.uk
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/intel.c |   11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 71492d2..b69d258 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -40,13 +40,14 @@ struct sku_microcode {
 	u32 microcode;
 };
 static const struct sku_microcode spectre_bad_microcodes[] = {
-	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0B,	0x84 },
-	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0A,	0x84 },
-	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x09,	0x84 },
-	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x0A,	0x84 },
-	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x09,	0x84 },
+	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0B,	0x80 },
+	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0A,	0x80 },
+	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x09,	0x80 },
+	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x0A,	0x80 },
+	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x09,	0x80 },
 	{ INTEL_FAM6_SKYLAKE_X,		0x03,	0x0100013e },
 	{ INTEL_FAM6_SKYLAKE_X,		0x04,	0x0200003c },
+	{ INTEL_FAM6_SKYLAKE_DESKTOP,	0x03,	0xc2 },
 	{ INTEL_FAM6_BROADWELL_CORE,	0x04,	0x28 },
 	{ INTEL_FAM6_BROADWELL_GT3E,	0x01,	0x1b },
 	{ INTEL_FAM6_BROADWELL_XEON_D,	0x02,	0x14 },

[PATCH 4.4.y 037/101] x86/speculation: Clean up various Spectre related details

[Srivatsa S. Bhat]

From: Ingo Molnar <mingo@kernel.org>

commit 21e433bdb95bdf3aa48226fd3d33af608437f293 upstream.

Harmonize all the Spectre messages so that a:

    dmesg | grep -i spectre

... gives us most Spectre related kernel boot messages.

Also fix a few other details:

 - clarify a comment about firmware speculation control

 - s/KPTI/PTI

 - remove various line-breaks that made the code uglier

Acked-by: David Woodhouse <dwmw@amazon.co.uk>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/bugs.c |   25 ++++++++++---------------
 1 file changed, 10 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 1968baf..fea368d 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -162,8 +162,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 	if (cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
 		return SPECTRE_V2_CMD_NONE;
 	else {
-		ret = cmdline_find_option(boot_command_line, "spectre_v2", arg,
-					  sizeof(arg));
+		ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg));
 		if (ret < 0)
 			return SPECTRE_V2_CMD_AUTO;
 
@@ -184,8 +183,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 	     cmd == SPECTRE_V2_CMD_RETPOLINE_AMD ||
 	     cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) &&
 	    !IS_ENABLED(CONFIG_RETPOLINE)) {
-		pr_err("%s selected but not compiled in. Switching to AUTO select\n",
-		       mitigation_options[i].option);
+		pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option);
 		return SPECTRE_V2_CMD_AUTO;
 	}
 
@@ -255,14 +253,14 @@ static void __init spectre_v2_select_mitigation(void)
 			goto retpoline_auto;
 		break;
 	}
-	pr_err("kernel not compiled with retpoline; no mitigation available!");
+	pr_err("Spectre mitigation: kernel not compiled with retpoline; no mitigation available!");
 	return;
 
 retpoline_auto:
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
 	retpoline_amd:
 		if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) {
-			pr_err("LFENCE not serializing. Switching to generic retpoline\n");
+			pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n");
 			goto retpoline_generic;
 		}
 		mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD :
@@ -280,7 +278,7 @@ retpoline_auto:
 	pr_info("%s\n", spectre_v2_strings[mode]);
 
 	/*
-	 * If neither SMEP or KPTI are available, there is a risk of
+	 * If neither SMEP nor PTI are available, there is a risk of
 	 * hitting userspace addresses in the RSB after a context switch
 	 * from a shallow call stack to a deeper one. To prevent this fill
 	 * the entire RSB, even when using IBRS.
@@ -294,21 +292,20 @@ retpoline_auto:
 	if ((!boot_cpu_has(X86_FEATURE_KAISER) &&
 	     !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) {
 		setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
-		pr_info("Filling RSB on context switch\n");
+		pr_info("Spectre v2 mitigation: Filling RSB on context switch\n");
 	}
 
 	/* Initialize Indirect Branch Prediction Barrier if supported */
 	if (boot_cpu_has(X86_FEATURE_IBPB)) {
 		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
-		pr_info("Enabling Indirect Branch Prediction Barrier\n");
+		pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n");
 	}
 }
 
 #undef pr_fmt
 
 #ifdef CONFIG_SYSFS
-ssize_t cpu_show_meltdown(struct device *dev,
-			  struct device_attribute *attr, char *buf)
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
 		return sprintf(buf, "Not affected\n");
@@ -317,16 +314,14 @@ ssize_t cpu_show_meltdown(struct device *dev,
 	return sprintf(buf, "Vulnerable\n");
 }
 
-ssize_t cpu_show_spectre_v1(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
 		return sprintf(buf, "Not affected\n");
 	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
 }
 
-ssize_t cpu_show_spectre_v2(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
 		return sprintf(buf, "Not affected\n");

[PATCH 4.4.y 038/101] x86/speculation: Fix up array_index_nospec_mask() asm constraint

[Srivatsa S. Bhat]

From: Dan Williams <dan.j.williams@intel.com>

commit be3233fbfcb8f5acb6e3bcd0895c3ef9e100d470 upstream.

Allow the compiler to handle @size as an immediate value or memory
directly rather than allocating a register.

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/151797010204.1289.1510000292250184993.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/barrier.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index e3a6f66..7f5dcb6 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -40,7 +40,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
 
 	asm volatile ("cmp %1,%2; sbb %0,%0;"
 			:"=r" (mask)
-			:"r"(size),"r" (index)
+			:"g"(size),"r" (index)
 			:"cc");
 	return mask;
 }

[PATCH 4.4.y 039/101] x86/speculation: Add <asm/msr-index.h> dependency

[Srivatsa S. Bhat]

From: Peter Zijlstra <peterz@infradead.org>

commit ea00f301285ea2f07393678cd2b6057878320c9d upstream.

Joe Konno reported a compile failure resulting from using an MSR
without inclusion of <asm/msr-index.h>, and while the current code builds
fine (by accident) this needs fixing for future patches.

Reported-by: Joe Konno <joe.konno@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: arjan@linux.intel.com
Cc: bp@alien8.de
Cc: dan.j.williams@intel.com
Cc: dave.hansen@linux.intel.com
Cc: dwmw2@infradead.org
Cc: dwmw@amazon.co.uk
Cc: gregkh@linuxfoundation.org
Cc: hpa@zytor.com
Cc: jpoimboe@redhat.com
Cc: linux-tip-commits@vger.kernel.org
Cc: luto@kernel.org
Fixes: 20ffa1caecca ("x86/speculation: Add basic IBPB (Indirect Branch Prediction Barrier) support")
Link: http://lkml.kernel.org/r/20180213132819.GJ25201@hirez.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/nospec-branch.h |    1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 8dcecb9..bca2860 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -6,6 +6,7 @@
 #include <asm/alternative.h>
 #include <asm/alternative-asm.h>
 #include <asm/cpufeatures.h>
+#include <asm/msr-index.h>
 
 /*
  * Fill the CPU return stack buffer.

[PATCH 4.4.y 040/101] x86/xen: Zero MSR_IA32_SPEC_CTRL before suspend

[Srivatsa S. Bhat]

From: Juergen Gross <jgross@suse.com>

commit 71c208dd54ab971036d83ff6d9837bae4976e623 upstream.

Older Xen versions (4.5 and before) might have problems migrating pv
guests with MSR_IA32_SPEC_CTRL having a non-zero value. So before
suspending zero that MSR and restore it after being resumed.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Cc: stable@vger.kernel.org
Cc: xen-devel@lists.xenproject.org
Cc: boris.ostrovsky@oracle.com
Link: https://lkml.kernel.org/r/20180226140818.4849-1-jgross@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/xen/suspend.c |   16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 7f664c4..4ecd0de 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -1,11 +1,14 @@
 #include <linux/types.h>
 #include <linux/tick.h>
+#include <linux/percpu-defs.h>
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
 #include <xen/grant_table.h>
 #include <xen/events.h>
 
+#include <asm/cpufeatures.h>
+#include <asm/msr-index.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/page.h>
 #include <asm/fixmap.h>
@@ -68,6 +71,8 @@ static void xen_pv_post_suspend(int suspend_cancelled)
 	xen_mm_unpin_all();
 }
 
+static DEFINE_PER_CPU(u64, spec_ctrl);
+
 void xen_arch_pre_suspend(void)
 {
 	if (xen_pv_domain())
@@ -84,6 +89,9 @@ void xen_arch_post_suspend(int cancelled)
 
 static void xen_vcpu_notify_restore(void *data)
 {
+	if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL))
+		wrmsrl(MSR_IA32_SPEC_CTRL, this_cpu_read(spec_ctrl));
+
 	/* Boot processor notified via generic timekeeping_resume() */
 	if (smp_processor_id() == 0)
 		return;
@@ -93,7 +101,15 @@ static void xen_vcpu_notify_restore(void *data)
 
 static void xen_vcpu_notify_suspend(void *data)
 {
+	u64 tmp;
+
 	tick_suspend_local();
+
+	if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL)) {
+		rdmsrl(MSR_IA32_SPEC_CTRL, tmp);
+		this_cpu_write(spec_ctrl, tmp);
+		wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+	}
 }
 
 void xen_arch_resume(void)

[PATCH 4.4.y 041/101] x86/mm: Factor out LDT init from context init

[Srivatsa S. Bhat]

From: Dave Hansen <dave.hansen@linux.intel.com>

commit 39a0526fb3f7d93433d146304278477eb463f8af upstream

The arch-specific mm_context_t is a great place to put
protection-key allocation state.

But, we need to initialize the allocation state because pkey 0 is
always "allocated".  All of the runtime initialization of
mm_context_t is done in *_ldt() manipulation functions.  This
renames the existing LDT functions like this:

	init_new_context() -> init_new_context_ldt()
	destroy_context() -> destroy_context_ldt()

and makes init_new_context() and destroy_context() available for
generic use.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/20160212210234.DB34FCC5@viggo.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/mmu_context.h |   21 ++++++++++++++++-----
 arch/x86/kernel/ldt.c              |    4 ++--
 2 files changed, 18 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 9bfc5fd..1c4794f 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -52,15 +52,15 @@ struct ldt_struct {
 /*
  * Used for LDT copy/destruction.
  */
-int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
-void destroy_context(struct mm_struct *mm);
+int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm);
+void destroy_context_ldt(struct mm_struct *mm);
 #else	/* CONFIG_MODIFY_LDT_SYSCALL */
-static inline int init_new_context(struct task_struct *tsk,
-				   struct mm_struct *mm)
+static inline int init_new_context_ldt(struct task_struct *tsk,
+				       struct mm_struct *mm)
 {
 	return 0;
 }
-static inline void destroy_context(struct mm_struct *mm) {}
+static inline void destroy_context_ldt(struct mm_struct *mm) {}
 #endif
 
 static inline void load_mm_ldt(struct mm_struct *mm)
@@ -102,6 +102,17 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 		this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
 }
 
+static inline int init_new_context(struct task_struct *tsk,
+				   struct mm_struct *mm)
+{
+	init_new_context_ldt(tsk, mm);
+	return 0;
+}
+static inline void destroy_context(struct mm_struct *mm)
+{
+	destroy_context_ldt(mm);
+}
+
 extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		      struct task_struct *tsk);
 
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index bc42936..8bc68cf 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -119,7 +119,7 @@ static void free_ldt_struct(struct ldt_struct *ldt)
  * we do not have to muck with descriptors here, that is
  * done in switch_mm() as needed.
  */
-int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm)
 {
 	struct ldt_struct *new_ldt;
 	struct mm_struct *old_mm;
@@ -160,7 +160,7 @@ out_unlock:
  *
  * 64bit: Don't touch the LDT register - we're already in the next thread.
  */
-void destroy_context(struct mm_struct *mm)
+void destroy_context_ldt(struct mm_struct *mm)
 {
 	free_ldt_struct(mm->context.ldt);
 	mm->context.ldt = NULL;

[PATCH 4.4.y 042/101] x86/mm: Give each mm TLB flush generation a unique ID

[Srivatsa S. Bhat]

From: Andy Lutomirski <luto@kernel.org>

commit f39681ed0f48498b80455095376f11535feea332 upstream.

This adds two new variables to mmu_context_t: ctx_id and tlb_gen.
ctx_id uniquely identifies the mm_struct and will never be reused.
For a given mm_struct (and hence ctx_id), tlb_gen is a monotonic
count of the number of times that a TLB flush has been requested.
The pair (ctx_id, tlb_gen) can be used as an identifier for TLB
flush actions and will be used in subsequent patches to reliably
determine whether all needed TLB flushes have occurred on a given
CPU.

This patch is split out for ease of review.  By itself, it has no
real effect other than creating and updating the new variables.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Reviewed-by: Nadav Amit <nadav.amit@gmail.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/413a91c24dab3ed0caa5f4e4d017d87b0857f920.1498751203.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/mmu.h         |   15 +++++++++++++--
 arch/x86/include/asm/mmu_context.h |    4 ++++
 arch/x86/mm/tlb.c                  |    2 ++
 3 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 7680b76..3359dfe 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -3,12 +3,18 @@
 
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
+#include <linux/atomic.h>
 
 /*
- * The x86 doesn't have a mmu context, but
- * we put the segment information here.
+ * x86 has arch-specific MMU state beyond what lives in mm_struct.
  */
 typedef struct {
+	/*
+	 * ctx_id uniquely identifies this mm_struct.  A ctx_id will never
+	 * be reused, and zero is not a valid ctx_id.
+	 */
+	u64 ctx_id;
+
 #ifdef CONFIG_MODIFY_LDT_SYSCALL
 	struct ldt_struct *ldt;
 #endif
@@ -24,6 +30,11 @@ typedef struct {
 	atomic_t perf_rdpmc_allowed;	/* nonzero if rdpmc is allowed */
 } mm_context_t;
 
+#define INIT_MM_CONTEXT(mm)						\
+	.context = {							\
+		.ctx_id = 1,						\
+	}
+
 void leave_mm(int cpu);
 
 #endif /* _ASM_X86_MMU_H */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 1c4794f..effc127 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -11,6 +11,9 @@
 #include <asm/tlbflush.h>
 #include <asm/paravirt.h>
 #include <asm/mpx.h>
+
+extern atomic64_t last_mm_ctx_id;
+
 #ifndef CONFIG_PARAVIRT
 static inline void paravirt_activate_mm(struct mm_struct *prev,
 					struct mm_struct *next)
@@ -105,6 +108,7 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
+	mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id);
 	init_new_context_ldt(tsk, mm);
 	return 0;
 }
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 7cad01af..efec198 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -29,6 +29,8 @@
  *	Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
  */
 
+atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);
+
 struct flush_tlb_info {
 	struct mm_struct *flush_mm;
 	unsigned long flush_start;

[PATCH 4.4.y 043/101] x86/speculation: Use Indirect Branch Prediction Barrier in context switch

[Srivatsa S. Bhat]

From: Tim Chen <tim.c.chen@linux.intel.com>

commit 18bf3c3ea8ece8f03b6fc58508f2dfd23c7711c7 upstream.

Flush indirect branches when switching into a process that marked itself
non dumpable. This protects high value processes like gpg better,
without having too high performance overhead.

If done naïvely, we could switch to a kernel idle thread and then back
to the original process, such as:

    process A -> idle -> process A

In such scenario, we do not have to do IBPB here even though the process
is non-dumpable, as we are switching back to the same process after a
hiatus.

To avoid the redundant IBPB, which is expensive, we track the last mm
user context ID. The cost is to have an extra u64 mm context id to track
the last mm we were using before switching to the init_mm used by idle.
Avoiding the extra IBPB is probably worth the extra memory for this
common scenario.

For those cases where tlb_defer_switch_to_init_mm() returns true (non
PCID), lazy tlb will defer switch to init_mm, so we will not be changing
the mm for the process A -> idle -> process A switch. So IBPB will be
skipped for this case.

Thanks to the reviewers and Andy Lutomirski for the suggestion of
using ctx_id which got rid of the problem of mm pointer recycling.

Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: ak@linux.intel.com
Cc: karahmed@amazon.de
Cc: arjan@linux.intel.com
Cc: torvalds@linux-foundation.org
Cc: linux@dominikbrodowski.net
Cc: peterz@infradead.org
Cc: bp@alien8.de
Cc: luto@kernel.org
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/1517263487-3708-1-git-send-email-dwmw@amazon.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/tlbflush.h |    2 ++
 arch/x86/mm/tlb.c               |   31 +++++++++++++++++++++++++++++++
 2 files changed, 33 insertions(+)

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index e2a89d2..8ce07db 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -68,6 +68,8 @@ static inline void invpcid_flush_all_nonglobals(void)
 struct tlb_state {
 	struct mm_struct *active_mm;
 	int state;
+	/* last user mm's ctx id */
+	u64 last_ctx_id;
 
 	/*
 	 * Access to this CR4 shadow and to H/W CR4 is protected by
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index efec198..6d683bb 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -10,6 +10,7 @@
 
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
+#include <asm/nospec-branch.h>
 #include <asm/cache.h>
 #include <asm/apic.h>
 #include <asm/uv/uv.h>
@@ -106,6 +107,36 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	unsigned cpu = smp_processor_id();
 
 	if (likely(prev != next)) {
+		u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id);
+
+		/*
+		 * Avoid user/user BTB poisoning by flushing the branch
+		 * predictor when switching between processes. This stops
+		 * one process from doing Spectre-v2 attacks on another.
+		 *
+		 * As an optimization, flush indirect branches only when
+		 * switching into processes that disable dumping. This
+		 * protects high value processes like gpg, without having
+		 * too high performance overhead. IBPB is *expensive*!
+		 *
+		 * This will not flush branches when switching into kernel
+		 * threads. It will also not flush if we switch to idle
+		 * thread and back to the same process. It will flush if we
+		 * switch to a different non-dumpable process.
+		 */
+		if (tsk && tsk->mm &&
+		    tsk->mm->context.ctx_id != last_ctx_id &&
+		    get_dumpable(tsk->mm) != SUID_DUMP_USER)
+			indirect_branch_prediction_barrier();
+
+		/*
+		 * Record last user mm's context id, so we can avoid
+		 * flushing branch buffer with IBPB if we switch back
+		 * to the same user.
+		 */
+		if (next != &init_mm)
+			this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id);
+
 		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
 		this_cpu_write(cpu_tlbstate.active_mm, next);
 		cpumask_set_cpu(cpu, mm_cpumask(next));

[PATCH 4.4.y 044/101] x86/spectre_v2: Don't check microcode versions when running under hypervisors

[Srivatsa S. Bhat]

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

commit 36268223c1e9981d6cfc33aff8520b3bde4b8114 upstream.

As:

 1) It's known that hypervisors lie about the environment anyhow (host
    mismatch)

 2) Even if the hypervisor (Xen, KVM, VMWare, etc) provided a valid
    "correct" value, it all gets to be very murky when migration happens
    (do you provide the "new" microcode of the machine?).

And in reality the cloud vendors are the ones that should make sure that
the microcode that is running is correct and we should just sing lalalala
and trust them.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: Wanpeng Li <kernellwp@gmail.com>
Cc: kvm <kvm@vger.kernel.org>
Cc: Krčmář <rkrcmar@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20180226213019.GE9497@char.us.oracle.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/intel.c |    7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b69d258..dcc0349 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -68,6 +68,13 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
 {
 	int i;
 
+	/*
+	 * We know that the hypervisor lie to us on the microcode version so
+	 * we may as well hope that it is running the correct version.
+	 */
+	if (cpu_has(c, X86_FEATURE_HYPERVISOR))
+		return false;
+
 	for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) {
 		if (c->x86_model == spectre_bad_microcodes[i].model &&
 		    c->x86_mask == spectre_bad_microcodes[i].stepping)

[PATCH 4.4.y 045/101] x86/speculation: Use IBRS if available before calling into firmware

[Srivatsa S. Bhat]

From: David Woodhouse <dwmw@amazon.co.uk>

commit dd84441a797150dcc49298ec95c459a8891d8bb1 upstream.

Retpoline means the kernel is safe because it has no indirect branches.
But firmware isn't, so use IBRS for firmware calls if it's available.

Block preemption while IBRS is set, although in practice the call sites
already had to be doing that.

Ignore hpwdt.c for now. It's taking spinlocks and calling into firmware
code, from an NMI handler. I don't want to touch that with a bargepole.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: arjan.van.de.ven@intel.com
Cc: bp@alien8.de
Cc: dave.hansen@intel.com
Cc: jmattson@google.com
Cc: karahmed@amazon.de
Cc: kvm@vger.kernel.org
Cc: pbonzini@redhat.com
Cc: rkrcmar@redhat.com
Link: http://lkml.kernel.org/r/1519037457-7643-2-git-send-email-dwmw@amazon.co.uk
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Srivatsa: Backported to 4.4.y, patching the efi_call_virt() family of functions,
  which are the 4.4.y-equivalents of arch_efi_call_virt_setup()/teardown() ]
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/apm.h           |    6 +++++
 arch/x86/include/asm/cpufeatures.h   |    1 +
 arch/x86/include/asm/efi.h           |    7 ++++++
 arch/x86/include/asm/nospec-branch.h |   39 ++++++++++++++++++++++++++--------
 arch/x86/kernel/cpu/bugs.c           |   12 ++++++++++
 arch/x86/platform/efi/efi_64.c       |    3 +++
 6 files changed, 58 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h
index 20370c6..3d1ec41 100644
--- a/arch/x86/include/asm/apm.h
+++ b/arch/x86/include/asm/apm.h
@@ -6,6 +6,8 @@
 #ifndef _ASM_X86_MACH_DEFAULT_APM_H
 #define _ASM_X86_MACH_DEFAULT_APM_H
 
+#include <asm/nospec-branch.h>
+
 #ifdef APM_ZERO_SEGS
 #	define APM_DO_ZERO_SEGS \
 		"pushl %%ds\n\t" \
@@ -31,6 +33,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
 	 * N.B. We do NOT need a cld after the BIOS call
 	 * because we always save and restore the flags.
 	 */
+	firmware_restrict_branch_speculation_start();
 	__asm__ __volatile__(APM_DO_ZERO_SEGS
 		"pushl %%edi\n\t"
 		"pushl %%ebp\n\t"
@@ -43,6 +46,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
 		  "=S" (*esi)
 		: "a" (func), "b" (ebx_in), "c" (ecx_in)
 		: "memory", "cc");
+	firmware_restrict_branch_speculation_end();
 }
 
 static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in,
@@ -55,6 +59,7 @@ static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in,
 	 * N.B. We do NOT need a cld after the BIOS call
 	 * because we always save and restore the flags.
 	 */
+	firmware_restrict_branch_speculation_start();
 	__asm__ __volatile__(APM_DO_ZERO_SEGS
 		"pushl %%edi\n\t"
 		"pushl %%ebp\n\t"
@@ -67,6 +72,7 @@ static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in,
 		  "=S" (si)
 		: "a" (func), "b" (ebx_in), "c" (ecx_in)
 		: "memory", "cc");
+	firmware_restrict_branch_speculation_end();
 	return error;
 }
 
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 782005d..bc76bf3 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -202,6 +202,7 @@
 #define X86_FEATURE_KAISER	( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */
 
 #define X86_FEATURE_USE_IBPB	( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled*/
+#define X86_FEATURE_USE_IBRS_FW	( 7*32+22) /* "" Use IBRS during runtime firmware calls */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 0010c78..7e5a2ff 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -3,6 +3,7 @@
 
 #include <asm/fpu/api.h>
 #include <asm/pgtable.h>
+#include <asm/nospec-branch.h>
 
 /*
  * We map the EFI regions needed for runtime services non-contiguously,
@@ -39,8 +40,10 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...);
 ({									\
 	efi_status_t __s;						\
 	kernel_fpu_begin();						\
+	firmware_restrict_branch_speculation_start();			\
 	__s = ((efi_##f##_t __attribute__((regparm(0)))*)		\
 		efi.systab->runtime->f)(args);				\
+	firmware_restrict_branch_speculation_end();			\
 	kernel_fpu_end();						\
 	__s;								\
 })
@@ -49,8 +52,10 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...);
 #define __efi_call_virt(f, args...) \
 ({									\
 	kernel_fpu_begin();						\
+	firmware_restrict_branch_speculation_start();			\
 	((efi_##f##_t __attribute__((regparm(0)))*)			\
 		efi.systab->runtime->f)(args);				\
+	firmware_restrict_branch_speculation_end();			\
 	kernel_fpu_end();						\
 })
 
@@ -71,7 +76,9 @@ extern u64 asmlinkage efi_call(void *fp, ...);
 	efi_sync_low_kernel_mappings();					\
 	preempt_disable();						\
 	__kernel_fpu_begin();						\
+	firmware_restrict_branch_speculation_start();			\
 	__s = efi_call((void *)efi.systab->runtime->f, __VA_ARGS__);	\
+	firmware_restrict_branch_speculation_end();			\
 	__kernel_fpu_end();						\
 	preempt_enable();						\
 	__s;								\
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index bca2860..36ded24 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -195,17 +195,38 @@ static inline void vmexit_fill_RSB(void)
 #endif
 }
 
+#define alternative_msr_write(_msr, _val, _feature)		\
+	asm volatile(ALTERNATIVE("",				\
+				 "movl %[msr], %%ecx\n\t"	\
+				 "movl %[val], %%eax\n\t"	\
+				 "movl $0, %%edx\n\t"		\
+				 "wrmsr",			\
+				 _feature)			\
+		     : : [msr] "i" (_msr), [val] "i" (_val)	\
+		     : "eax", "ecx", "edx", "memory")
+
 static inline void indirect_branch_prediction_barrier(void)
 {
-	asm volatile(ALTERNATIVE("",
-				 "movl %[msr], %%ecx\n\t"
-				 "movl %[val], %%eax\n\t"
-				 "movl $0, %%edx\n\t"
-				 "wrmsr",
-				 X86_FEATURE_USE_IBPB)
-		     : : [msr] "i" (MSR_IA32_PRED_CMD),
-			 [val] "i" (PRED_CMD_IBPB)
-		     : "eax", "ecx", "edx", "memory");
+	alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB,
+			      X86_FEATURE_USE_IBPB);
+}
+
+/*
+ * With retpoline, we must use IBRS to restrict branch prediction
+ * before calling into firmware.
+ */
+static inline void firmware_restrict_branch_speculation_start(void)
+{
+	preempt_disable();
+	alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS,
+			      X86_FEATURE_USE_IBRS_FW);
+}
+
+static inline void firmware_restrict_branch_speculation_end(void)
+{
+	alternative_msr_write(MSR_IA32_SPEC_CTRL, 0,
+			      X86_FEATURE_USE_IBRS_FW);
+	preempt_enable();
 }
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index fea368d..b294fdc 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -300,6 +300,15 @@ retpoline_auto:
 		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
 		pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n");
 	}
+
+	/*
+	 * Retpoline means the kernel is safe because it has no indirect
+	 * branches. But firmware isn't, so use IBRS to protect that.
+	 */
+	if (boot_cpu_has(X86_FEATURE_IBRS)) {
+		setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
+		pr_info("Enabling Restricted Speculation for firmware calls\n");
+	}
 }
 
 #undef pr_fmt
@@ -326,8 +335,9 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
 		return sprintf(buf, "Not affected\n");
 
-	return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+	return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
 		       boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
+		       boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
 		       spectre_v2_module_string());
 }
 #endif
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index a0ac0f9..f5a8cd9 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -40,6 +40,7 @@
 #include <asm/fixmap.h>
 #include <asm/realmode.h>
 #include <asm/time.h>
+#include <asm/nospec-branch.h>
 
 /*
  * We allocate runtime services regions bottom-up, starting from -4G, i.e.
@@ -347,6 +348,7 @@ extern efi_status_t efi64_thunk(u32, ...);
 									\
 	efi_sync_low_kernel_mappings();					\
 	local_irq_save(flags);						\
+	firmware_restrict_branch_speculation_start();			\
 									\
 	efi_scratch.prev_cr3 = read_cr3();				\
 	write_cr3((unsigned long)efi_scratch.efi_pgt);			\
@@ -357,6 +359,7 @@ extern efi_status_t efi64_thunk(u32, ...);
 									\
 	write_cr3(efi_scratch.prev_cr3);				\
 	__flush_tlb_all();						\
+	firmware_restrict_branch_speculation_end();			\
 	local_irq_restore(flags);					\
 									\
 	__s;								\

[PATCH 4.4.y 046/101] x86/speculation: Move firmware_restrict_branch_speculation_*() from C to CPP

[Srivatsa S. Bhat]

From: Ingo Molnar <mingo@kernel.org>

commit d72f4e29e6d84b7ec02ae93088aa459ac70e733b upstream.

firmware_restrict_branch_speculation_*() recently started using
preempt_enable()/disable(), but those are relatively high level
primitives and cause build failures on some 32-bit builds.

Since we want to keep <asm/nospec-branch.h> low level, convert
them to macros to avoid header hell...

Cc: David Woodhouse <dwmw@amazon.co.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: arjan.van.de.ven@intel.com
Cc: bp@alien8.de
Cc: dave.hansen@intel.com
Cc: jmattson@google.com
Cc: karahmed@amazon.de
Cc: kvm@vger.kernel.org
Cc: pbonzini@redhat.com
Cc: rkrcmar@redhat.com
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/nospec-branch.h |   26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 36ded24..b9dd1d9 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -214,20 +214,22 @@ static inline void indirect_branch_prediction_barrier(void)
 /*
  * With retpoline, we must use IBRS to restrict branch prediction
  * before calling into firmware.
+ *
+ * (Implemented as CPP macros due to header hell.)
  */
-static inline void firmware_restrict_branch_speculation_start(void)
-{
-	preempt_disable();
-	alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS,
-			      X86_FEATURE_USE_IBRS_FW);
-}
+#define firmware_restrict_branch_speculation_start()			\
+do {									\
+	preempt_disable();						\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS,	\
+			      X86_FEATURE_USE_IBRS_FW);			\
+} while (0)
 
-static inline void firmware_restrict_branch_speculation_end(void)
-{
-	alternative_msr_write(MSR_IA32_SPEC_CTRL, 0,
-			      X86_FEATURE_USE_IBRS_FW);
-	preempt_enable();
-}
+#define firmware_restrict_branch_speculation_end()			\
+do {									\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL, 0,			\
+			      X86_FEATURE_USE_IBRS_FW);			\
+	preempt_enable();						\
+} while (0)
 
 #endif /* __ASSEMBLY__ */
 

[PATCH 4.4.y 047/101] x86/speculation: Remove Skylake C2 from Speculation Control microcode blacklist

[Srivatsa S. Bhat]

From: Alexander Sergeyev <sergeev917@gmail.com>

commit e3b3121fa8da94cb20f9e0c64ab7981ae47fd085 upstream.

In accordance with Intel's microcode revision guidance from March 6 MCU
rev 0xc2 is cleared on both Skylake H/S and Skylake Xeon E3 processors
that share CPUID 506E3.

Signed-off-by: Alexander Sergeyev <sergeev917@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Jia Zhang <qianyue.zj@alibaba-inc.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Kyle Huey <me@kylehuey.com>
Cc: David Woodhouse <dwmw@amazon.co.uk>
Link: https://lkml.kernel.org/r/20180313193856.GA8580@localhost.localdomain
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/intel.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index dcc0349..77d9f68 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -29,7 +29,7 @@
 /*
  * Early microcode releases for the Spectre v2 mitigation were broken.
  * Information taken from;
- * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/01/microcode-update-guidance.pdf
+ * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/03/microcode-update-guidance.pdf
  * - https://kb.vmware.com/s/article/52345
  * - Microcode revisions observed in the wild
  * - Release note from 20180108 microcode release
@@ -47,7 +47,6 @@ static const struct sku_microcode spectre_bad_microcodes[] = {
 	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x09,	0x80 },
 	{ INTEL_FAM6_SKYLAKE_X,		0x03,	0x0100013e },
 	{ INTEL_FAM6_SKYLAKE_X,		0x04,	0x0200003c },
-	{ INTEL_FAM6_SKYLAKE_DESKTOP,	0x03,	0xc2 },
 	{ INTEL_FAM6_BROADWELL_CORE,	0x04,	0x28 },
 	{ INTEL_FAM6_BROADWELL_GT3E,	0x01,	0x1b },
 	{ INTEL_FAM6_BROADWELL_XEON_D,	0x02,	0x14 },

[PATCH 4.4.y 048/101] selftest/seccomp: Fix the flag name SECCOMP_FILTER_FLAG_TSYNC

[Srivatsa S. Bhat]

From: Mickaël Salaün <mic@digikod.net>

commit 6c045d07bb305c527140bdec4cf8ab50f7c980d8 upstream

Rename SECCOMP_FLAG_FILTER_TSYNC to SECCOMP_FILTER_FLAG_TSYNC to match
the UAPI.

Signed-off-by: Mickaël Salaün <mic@digikod.net>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Kees Cook <keescook@chromium.org>
Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Will Drewry <wad@chromium.org>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 tools/testing/selftests/seccomp/seccomp_bpf.c |   18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 882fe83..d446346 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -1476,8 +1476,8 @@ TEST_F(TRACE_syscall, syscall_dropped)
 #define SECCOMP_SET_MODE_FILTER 1
 #endif
 
-#ifndef SECCOMP_FLAG_FILTER_TSYNC
-#define SECCOMP_FLAG_FILTER_TSYNC 1
+#ifndef SECCOMP_FILTER_FLAG_TSYNC
+#define SECCOMP_FILTER_FLAG_TSYNC 1
 #endif
 
 #ifndef seccomp
@@ -1592,7 +1592,7 @@ TEST(TSYNC_first)
 		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
 	}
 
-	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
 		      &prog);
 	ASSERT_NE(ENOSYS, errno) {
 		TH_LOG("Kernel does not support seccomp syscall!");
@@ -1810,7 +1810,7 @@ TEST_F(TSYNC, two_siblings_with_ancestor)
 		self->sibling_count++;
 	}
 
-	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
 		      &self->apply_prog);
 	ASSERT_EQ(0, ret) {
 		TH_LOG("Could install filter on all threads!");
@@ -1871,7 +1871,7 @@ TEST_F(TSYNC, two_siblings_with_no_filter)
 		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
 	}
 
-	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
 		      &self->apply_prog);
 	ASSERT_NE(ENOSYS, errno) {
 		TH_LOG("Kernel does not support seccomp syscall!");
@@ -1919,7 +1919,7 @@ TEST_F(TSYNC, two_siblings_with_one_divergence)
 		self->sibling_count++;
 	}
 
-	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
 		      &self->apply_prog);
 	ASSERT_EQ(self->sibling[0].system_tid, ret) {
 		TH_LOG("Did not fail on diverged sibling.");
@@ -1971,7 +1971,7 @@ TEST_F(TSYNC, two_siblings_not_under_filter)
 		TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER!");
 	}
 
-	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
 		      &self->apply_prog);
 	ASSERT_EQ(ret, self->sibling[0].system_tid) {
 		TH_LOG("Did not fail on diverged sibling.");
@@ -2000,7 +2000,7 @@ TEST_F(TSYNC, two_siblings_not_under_filter)
 	/* Switch to the remaining sibling */
 	sib = !sib;
 
-	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
 		      &self->apply_prog);
 	ASSERT_EQ(0, ret) {
 		TH_LOG("Expected the remaining sibling to sync");
@@ -2023,7 +2023,7 @@ TEST_F(TSYNC, two_siblings_not_under_filter)
 	while (!kill(self->sibling[sib].system_tid, 0))
 		sleep(0.1);
 
-	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
 		      &self->apply_prog);
 	ASSERT_EQ(0, ret);  /* just us chickens */
 }

[PATCH 4.4.y 049/101] selftest/seccomp: Fix the seccomp(2) signature

[Srivatsa S. Bhat]

From: Mickaël Salaün <mic@digikod.net>

commit 505ce68c6da3432454c62e43c24a22ea5b1d754b upstream

Signed-off-by: Mickaël Salaün <mic@digikod.net>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Kees Cook <keescook@chromium.org>
Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Will Drewry <wad@chromium.org>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 tools/testing/selftests/seccomp/seccomp_bpf.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index d446346..29487e0 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -1481,10 +1481,10 @@ TEST_F(TRACE_syscall, syscall_dropped)
 #endif
 
 #ifndef seccomp
-int seccomp(unsigned int op, unsigned int flags, struct sock_fprog *filter)
+int seccomp(unsigned int op, unsigned int flags, void *args)
 {
 	errno = 0;
-	return syscall(__NR_seccomp, op, flags, filter);
+	return syscall(__NR_seccomp, op, flags, args);
 }
 #endif
 

[PATCH 4.4.y 050/101] xen: set cpu capabilities from xen_start_kernel()

[Srivatsa S. Bhat]

From: Juergen Gross <jgross@suse.com>

Upstream commit: 0808e80cb760de2733c0527d2090ed2205a1eef8 ("xen: set
cpu capabilities from xen_start_kernel()")

There is no need to set the same capabilities for each cpu
individually. This can easily be done for all cpus when starting the
kernel.

Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/xen/enlighten.c |   18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index cbef64b..2d7ab4e 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -460,6 +460,14 @@ static void __init xen_init_cpuid_mask(void)
 		cpuid_leaf1_ecx_set_mask = (1 << (X86_FEATURE_MWAIT % 32));
 }
 
+static void __init xen_init_capabilities(void)
+{
+	if (xen_pv_domain()) {
+		setup_clear_cpu_cap(X86_BUG_SYSRET_SS_ATTRS);
+		setup_force_cpu_cap(X86_FEATURE_XENPV);
+	}
+}
+
 static void xen_set_debugreg(int reg, unsigned long val)
 {
 	HYPERVISOR_set_debugreg(reg, val);
@@ -1587,6 +1595,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 
 	xen_init_irq_ops();
 	xen_init_cpuid_mask();
+	xen_init_capabilities();
 
 #ifdef CONFIG_X86_LOCAL_APIC
 	/*
@@ -1883,14 +1892,6 @@ bool xen_hvm_need_lapic(void)
 }
 EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);
 
-static void xen_set_cpu_features(struct cpuinfo_x86 *c)
-{
-	if (xen_pv_domain()) {
-		clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
-		set_cpu_cap(c, X86_FEATURE_XENPV);
-	}
-}
-
 const struct hypervisor_x86 x86_hyper_xen = {
 	.name			= "Xen",
 	.detect			= xen_platform,
@@ -1898,7 +1899,6 @@ const struct hypervisor_x86 x86_hyper_xen = {
 	.init_platform		= xen_hvm_guest_init,
 #endif
 	.x2apic_available	= xen_x2apic_para_available,
-	.set_cpu_features       = xen_set_cpu_features,
 };
 EXPORT_SYMBOL(x86_hyper_xen);
 

[PATCH 4.4.y 051/101] x86/amd: don't set X86_BUG_SYSRET_SS_ATTRS when running under Xen

[Srivatsa S. Bhat]

From: David Woodhouse <dwmw@amazon.co.uk>

commit def9331a12977770cc6132d79f8e6565871e8e38 upstream

When running as Xen pv guest X86_BUG_SYSRET_SS_ATTRS must not be set
on AMD cpus.

This bug/feature bit is kind of special as it will be used very early
when switching threads. Setting the bit and clearing it a little bit
later leaves a critical window where things can go wrong. This time
window has enlarged a little bit by using setup_clear_cpu_cap() instead
of the hypervisor's set_cpu_features callback. It seems this larger
window now makes it rather easy to hit the problem.

The proper solution is to never set the bit in case of Xen.

Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/amd.c |    5 +++--
 arch/x86/xen/enlighten.c  |    4 +---
 2 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f4fb8f5..9b29414 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -791,8 +791,9 @@ static void init_amd(struct cpuinfo_x86 *c)
 		if (cpu_has(c, X86_FEATURE_3DNOW) || cpu_has(c, X86_FEATURE_LM))
 			set_cpu_cap(c, X86_FEATURE_3DNOWPREFETCH);
 
-	/* AMD CPUs don't reset SS attributes on SYSRET */
-	set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+	/* AMD CPUs don't reset SS attributes on SYSRET, Xen does. */
+	if (!cpu_has(c, X86_FEATURE_XENPV))
+		set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 2d7ab4e..82fd84d 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -462,10 +462,8 @@ static void __init xen_init_cpuid_mask(void)
 
 static void __init xen_init_capabilities(void)
 {
-	if (xen_pv_domain()) {
-		setup_clear_cpu_cap(X86_BUG_SYSRET_SS_ATTRS);
+	if (xen_pv_domain())
 		setup_force_cpu_cap(X86_FEATURE_XENPV);
-	}
 }
 
 static void xen_set_debugreg(int reg, unsigned long val)

Re: [PATCH 4.4.y 051/101] x86/amd: don't set X86_BUG_SYSRET_SS_ATTRS when running under Xen

[Juergen Gross]

On 14/07/18 11:33, Srivatsa S. Bhat wrote:
> From: David Woodhouse <dwmw@amazon.co.uk>
> 
> commit def9331a12977770cc6132d79f8e6565871e8e38 upstream
> 
> When running as Xen pv guest X86_BUG_SYSRET_SS_ATTRS must not be set
> on AMD cpus.
> 
> This bug/feature bit is kind of special as it will be used very early
> when switching threads. Setting the bit and clearing it a little bit
> later leaves a critical window where things can go wrong. This time
> window has enlarged a little bit by using setup_clear_cpu_cap() instead
> of the hypervisor's set_cpu_features callback. It seems this larger
> window now makes it rather easy to hit the problem.
> 
> The proper solution is to never set the bit in case of Xen.
> 
> Signed-off-by: Juergen Gross <jgross@suse.com>
> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
> Acked-by: Thomas Gleixner <tglx@linutronix.de>
> Signed-off-by: Juergen Gross <jgross@suse.com>
> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
> Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
> Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
> Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
> Reviewed-by: Bo Gan <ganb@vmware.com>

I believe you'll need upstream commit
60d3450167433f2d099ce2869dc52dd9e7dc9b29 ("x86/cpu: Re-apply forced caps
every time CPU caps are re-read") for this patch to work as intended.

It was necessary for 4.9, at least.


Juergen

Re: [PATCH 4.4.y 051/101] x86/amd: don't set X86_BUG_SYSRET_SS_ATTRS when running under Xen

[Srivatsa S. Bhat]

[-- Attachment #1: Type: text/plain, Size: 2224 bytes --]

On 7/14/18 7:15 AM, Juergen Gross wrote:
> On 14/07/18 11:33, Srivatsa S. Bhat wrote:
>> From: David Woodhouse <dwmw@amazon.co.uk>
>>
>> commit def9331a12977770cc6132d79f8e6565871e8e38 upstream
>>
>> When running as Xen pv guest X86_BUG_SYSRET_SS_ATTRS must not be set
>> on AMD cpus.
>>
>> This bug/feature bit is kind of special as it will be used very early
>> when switching threads. Setting the bit and clearing it a little bit
>> later leaves a critical window where things can go wrong. This time
>> window has enlarged a little bit by using setup_clear_cpu_cap() instead
>> of the hypervisor's set_cpu_features callback. It seems this larger
>> window now makes it rather easy to hit the problem.
>>
>> The proper solution is to never set the bit in case of Xen.
>>
>> Signed-off-by: Juergen Gross <jgross@suse.com>
>> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
>> Acked-by: Thomas Gleixner <tglx@linutronix.de>
>> Signed-off-by: Juergen Gross <jgross@suse.com>
>> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
>> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
>> Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
>> Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
>> Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
>> Reviewed-by: Bo Gan <ganb@vmware.com>
> 
> I believe you'll need upstream commit
> 60d3450167433f2d099ce2869dc52dd9e7dc9b29 ("x86/cpu: Re-apply forced caps
> every time CPU caps are re-read") for this patch to work as intended.
> 
> It was necessary for 4.9, at least.
> 

Ah, I see. Thank you for letting me know, Juergen! Looking at 4.9.112,
I see that in addition to the patch you mentioned above, we should
also backport this patch to 4.4: upstream commit 74899d92e66663dc7671a
x6/xen: Add call of speculative_store_bypass_ht_init() to PV paths

The 4.9 backports of these patches apply cleanly to 4.4 as well, but I
have attached them anyway with this mail. Greg, could you consider
queuing these 2 patches for 4.4 at the end of this patch series?

1. x86/xen: Add call of speculative_store_bypass_ht_init() to PV paths
2. x86/cpu: Re-apply forced caps every time CPU caps are re-read

Thank you!

Regards,
Srivatsa
VMware Photon OS

[-- Attachment #2: 0001-x86-xen-Add-call-of-speculative_store_bypass_ht_init.patch --]
[-- Type: text/plain, Size: 2059 bytes --]

From 9dee2b7c4d4868423d9812c969b0b724fdf780c6 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Thu, 21 Jun 2018 10:43:31 +0200
Subject: [PATCH 1/2] x86/xen: Add call of speculative_store_bypass_ht_init()
 to PV paths

commit 74899d92e66663dc7671a8017b3146dcd4735f3b upstream.

Commit:

  1f50ddb4f418 ("x86/speculation: Handle HT correctly on AMD")

... added speculative_store_bypass_ht_init() to the per-CPU initialization sequence.

speculative_store_bypass_ht_init() needs to be called on each CPU for
PV guests, too.

Reported-by: Brian Woods <brian.woods@amd.com>
Tested-by: Brian Woods <brian.woods@amd.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Cc: <stable@vger.kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: boris.ostrovsky@oracle.com
Cc: xen-devel@lists.xenproject.org
Fixes: 1f50ddb4f4189243c05926b842dc1a0332195f31 ("x86/speculation: Handle HT correctly on AMD")
Link: https://lore.kernel.org/lkml/20180621084331.21228-1-jgross@suse.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
---
 arch/x86/xen/smp.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 3f4ebf0..29e50d1 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -28,6 +28,7 @@
 #include <xen/interface/vcpu.h>
 #include <xen/interface/xenpmu.h>
 
+#include <asm/spec-ctrl.h>
 #include <asm/xen/interface.h>
 #include <asm/xen/hypercall.h>
 
@@ -87,6 +88,8 @@ static void cpu_bringup(void)
 	cpu_data(cpu).x86_max_cores = 1;
 	set_cpu_sibling_map(cpu);
 
+	speculative_store_bypass_ht_init();
+
 	xen_setup_cpu_clockevents();
 
 	notify_cpu_starting(cpu);
@@ -357,6 +360,8 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
 	}
 	set_cpu_sibling_map(0);
 
+	speculative_store_bypass_ht_init();
+
 	xen_pmu_init(0);
 
 	if (xen_smp_intr_init(0))
-- 
2.7.4


[-- Attachment #3: 0002-x86-cpu-Re-apply-forced-caps-every-time-CPU-caps-are.patch --]
[-- Type: text/plain, Size: 2278 bytes --]

From bdda88b5f410398f03ec6bb294cce07173232ea8 Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@kernel.org>
Date: Wed, 18 Jan 2017 11:15:39 -0800
Subject: [PATCH 2/2] x86/cpu: Re-apply forced caps every time CPU caps are
 re-read

commit 60d3450167433f2d099ce2869dc52dd9e7dc9b29 upstream.

Calling get_cpu_cap() will reset a bunch of CPU features.  This will
cause the system to lose track of force-set and force-cleared
features in the words that are reset until the end of CPU
initialization.  This can cause X86_FEATURE_FPU, for example, to
change back and forth during boot and potentially confuse CPU setup.

To minimize the chance of confusion, re-apply forced caps every time
get_cpu_cap() is called.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Reviewed-by: Borislav Petkov <bp@suse.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matthew Whitehead <tedheadster@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: One Thousand Gnomes <gnomes@lxorguk.ukuu.org.uk>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Yu-cheng Yu <yu-cheng.yu@intel.com>
Link: http://lkml.kernel.org/r/c817eb373d2c67c2c81413a70fc9b845fa34a37e.1484705016.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
---
 arch/x86/kernel/cpu/common.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9ad38ad..3d21b28 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -803,6 +803,13 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 
 	init_scattered_cpuid_features(c);
 	init_speculation_control(c);
+
+	/*
+	 * Clear/Set all flags overridden by options, after probe.
+	 * This needs to happen each time we re-probe, which may happen
+	 * several times during CPU initialization.
+	 */
+	apply_forced_caps(c);
 }
 
 static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
-- 
2.7.4

[PATCH 4.4.y 052/101] x86/nospec: Simplify alternative_msr_write()

[Srivatsa S. Bhat]

From: Linus Torvalds <torvalds@linux-foundation.org>

commit 1aa7a5735a41418d8e01fa7c9565eb2657e2ea3f upstream

The macro is not type safe and I did look for why that "g" constraint for
the asm doesn't work: it's because the asm is more fundamentally wrong.

It does

        movl %[val], %%eax

but "val" isn't a 32-bit value, so then gcc will pass it in a register,
and generate code like

        movl %rsi, %eax

and gas will complain about a nonsensical 'mov' instruction (it's moving a
64-bit register to a 32-bit one).

Passing it through memory will just hide the real bug - gcc still thinks
the memory location is 64-bit, but the "movl" will only load the first 32
bits and it all happens to work because x86 is little-endian.

Convert it to a type safe inline function with a little trick which hands
the feature into the ALTERNATIVE macro.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/nospec-branch.h |   19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index b9dd1d9..6403016 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -195,15 +195,16 @@ static inline void vmexit_fill_RSB(void)
 #endif
 }
 
-#define alternative_msr_write(_msr, _val, _feature)		\
-	asm volatile(ALTERNATIVE("",				\
-				 "movl %[msr], %%ecx\n\t"	\
-				 "movl %[val], %%eax\n\t"	\
-				 "movl $0, %%edx\n\t"		\
-				 "wrmsr",			\
-				 _feature)			\
-		     : : [msr] "i" (_msr), [val] "i" (_val)	\
-		     : "eax", "ecx", "edx", "memory")
+static __always_inline
+void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
+{
+	asm volatile(ALTERNATIVE("", "wrmsr", %c[feature])
+		: : "c" (msr),
+		    "a" (val),
+		    "d" (val >> 32),
+		    [feature] "i" (feature)
+		: "memory");
+}
 
 static inline void indirect_branch_prediction_barrier(void)
 {

[PATCH 4.4.y 053/101] x86/bugs: Concentrate bug detection into a separate function

[Srivatsa S. Bhat]

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

commit 4a28bfe3267b68e22c663ac26185aa16c9b879ef upstream

Combine the various logic which goes through all those
x86_cpu_id matching structures in one function.

Suggested-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/common.c |   21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 48499b4..97558d1 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -835,21 +835,27 @@ static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
 	{}
 };
 
-static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c)
+static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 ia32_cap = 0;
 
+	if (x86_match_cpu(cpu_no_speculation))
+		return;
+
+	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
+	setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
+
 	if (x86_match_cpu(cpu_no_meltdown))
-		return false;
+		return;
 
 	if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
 		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
 
 	/* Rogue Data Cache Load? No! */
 	if (ia32_cap & ARCH_CAP_RDCL_NO)
-		return false;
+		return;
 
-	return true;
+	setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
 }
 
 /*
@@ -898,12 +904,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
 
-	if (!x86_match_cpu(cpu_no_speculation)) {
-		if (cpu_vulnerable_to_meltdown(c))
-			setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
-		setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
-		setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
-	}
+	cpu_set_bug_bits(c);
 
 	fpu__init_system(c);
 

[PATCH 4.4.y 054/101] x86/bugs: Concentrate bug reporting into a separate function

[Srivatsa S. Bhat]

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

commit d1059518b4789cabe34bb4b714d07e6089c82ca1 upstream

Those SysFS functions have a similar preamble, as such make common
code to handle them.

Suggested-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/bugs.c |   46 +++++++++++++++++++++++++++++++-------------
 1 file changed, 32 insertions(+), 14 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index b294fdc..75f3d49 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -314,30 +314,48 @@ retpoline_auto:
 #undef pr_fmt
 
 #ifdef CONFIG_SYSFS
-ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
+
+ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
+			char *buf, unsigned int bug)
 {
-	if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+	if (!boot_cpu_has_bug(bug))
 		return sprintf(buf, "Not affected\n");
-	if (boot_cpu_has(X86_FEATURE_KAISER))
-		return sprintf(buf, "Mitigation: PTI\n");
+
+	switch (bug) {
+	case X86_BUG_CPU_MELTDOWN:
+		if (boot_cpu_has(X86_FEATURE_KAISER))
+			return sprintf(buf, "Mitigation: PTI\n");
+
+		break;
+
+	case X86_BUG_SPECTRE_V1:
+		return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+
+	case X86_BUG_SPECTRE_V2:
+		return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+			       boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
+			       boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
+			       spectre_v2_module_string());
+
+	default:
+		break;
+	}
+
 	return sprintf(buf, "Vulnerable\n");
 }
 
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_CPU_MELTDOWN);
+}
+
 ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
-		return sprintf(buf, "Not affected\n");
-	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+	return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V1);
 }
 
 ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
-		return sprintf(buf, "Not affected\n");
-
-	return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
-		       boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
-		       boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
-		       spectre_v2_module_string());
+	return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V2);
 }
 #endif

[PATCH 4.4.y 055/101] x86/bugs: Read SPEC_CTRL MSR during boot and re-use reserved bits

[Srivatsa S. Bhat]

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

commit 1b86883ccb8d5d9506529d42dbe1a5257cb30b18 upstream

The 336996-Speculative-Execution-Side-Channel-Mitigations.pdf refers to all
the other bits as reserved. The Intel SDM glossary defines reserved as
implementation specific - aka unknown.

As such at bootup this must be taken it into account and proper masking for
the bits in use applied.

A copy of this document is available at
https://bugzilla.kernel.org/show_bug.cgi?id=199511

[ tglx: Made x86_spec_ctrl_base __ro_after_init ]
[ Srivatsa: Removed __ro_after_init for 4.4.y ]

Suggested-by: Jon Masters <jcm@redhat.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/nospec-branch.h |   24 ++++++++++++++++++++----
 arch/x86/kernel/cpu/bugs.c           |   27 +++++++++++++++++++++++++++
 2 files changed, 47 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 6403016..daec318 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -172,6 +172,17 @@ enum spectre_v2_mitigation {
 	SPECTRE_V2_IBRS,
 };
 
+/*
+ * The Intel specification for the SPEC_CTRL MSR requires that we
+ * preserve any already set reserved bits at boot time (e.g. for
+ * future additions that this kernel is not currently aware of).
+ * We then set any additional mitigation bits that we want
+ * ourselves and always use this as the base for SPEC_CTRL.
+ * We also use this when handling guest entry/exit as below.
+ */
+extern void x86_spec_ctrl_set(u64);
+extern u64 x86_spec_ctrl_get_default(void);
+
 extern char __indirect_thunk_start[];
 extern char __indirect_thunk_end[];
 
@@ -208,8 +219,9 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
 
 static inline void indirect_branch_prediction_barrier(void)
 {
-	alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB,
-			      X86_FEATURE_USE_IBPB);
+	u64 val = PRED_CMD_IBPB;
+
+	alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB);
 }
 
 /*
@@ -220,14 +232,18 @@ static inline void indirect_branch_prediction_barrier(void)
  */
 #define firmware_restrict_branch_speculation_start()			\
 do {									\
+	u64 val = x86_spec_ctrl_get_default() | SPEC_CTRL_IBRS;		\
+									\
 	preempt_disable();						\
-	alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS,	\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL, val,			\
 			      X86_FEATURE_USE_IBRS_FW);			\
 } while (0)
 
 #define firmware_restrict_branch_speculation_end()			\
 do {									\
-	alternative_msr_write(MSR_IA32_SPEC_CTRL, 0,			\
+	u64 val = x86_spec_ctrl_get_default();				\
+									\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL, val,			\
 			      X86_FEATURE_USE_IBRS_FW);			\
 	preempt_enable();						\
 } while (0)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 75f3d49..42c2204 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -27,6 +27,12 @@
 
 static void __init spectre_v2_select_mitigation(void);
 
+/*
+ * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any
+ * writes to SPEC_CTRL contain whatever reserved bits have been set.
+ */
+static u64 x86_spec_ctrl_base;
+
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
@@ -36,6 +42,13 @@ void __init check_bugs(void)
 		print_cpu_info(&boot_cpu_data);
 	}
 
+	/*
+	 * Read the SPEC_CTRL MSR to account for reserved bits which may
+	 * have unknown values.
+	 */
+	if (boot_cpu_has(X86_FEATURE_IBRS))
+		rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+
 	/* Select the proper spectre mitigation before patching alternatives */
 	spectre_v2_select_mitigation();
 
@@ -94,6 +107,20 @@ static const char *spectre_v2_strings[] = {
 
 static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE;
 
+void x86_spec_ctrl_set(u64 val)
+{
+	if (val & ~SPEC_CTRL_IBRS)
+		WARN_ONCE(1, "SPEC_CTRL MSR value 0x%16llx is unknown.\n", val);
+	else
+		wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base | val);
+}
+EXPORT_SYMBOL_GPL(x86_spec_ctrl_set);
+
+u64 x86_spec_ctrl_get_default(void)
+{
+	return x86_spec_ctrl_base;
+}
+EXPORT_SYMBOL_GPL(x86_spec_ctrl_get_default);
 
 #ifdef RETPOLINE
 static bool spectre_v2_bad_module;

[PATCH 4.4.y 056/101] x86/bugs, KVM: Support the combination of guest and host IBRS

[Srivatsa S. Bhat]

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

commit 5cf687548705412da47c9cec342fd952d71ed3d5 upstream

A guest may modify the SPEC_CTRL MSR from the value used by the
kernel. Since the kernel doesn't use IBRS, this means a value of zero is
what is needed in the host.

But the 336996-Speculative-Execution-Side-Channel-Mitigations.pdf refers to
the other bits as reserved so the kernel should respect the boot time
SPEC_CTRL value and use that.

This allows to deal with future extensions to the SPEC_CTRL interface if
any at all.

Note: This uses wrmsrl() instead of native_wrmsl(). I does not make any
difference as paravirt will over-write the callq *0xfff.. with the wrmsrl
assembler code.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Srivatsa: Backported to 4.4.y, skipping the KVM changes in this patch. ]
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/nospec-branch.h |   10 ++++++++++
 arch/x86/kernel/cpu/bugs.c           |   18 ++++++++++++++++++
 2 files changed, 28 insertions(+)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index daec318..11db69a 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -183,6 +183,16 @@ enum spectre_v2_mitigation {
 extern void x86_spec_ctrl_set(u64);
 extern u64 x86_spec_ctrl_get_default(void);
 
+/*
+ * On VMENTER we must preserve whatever view of the SPEC_CTRL MSR
+ * the guest has, while on VMEXIT we restore the host view. This
+ * would be easier if SPEC_CTRL were architecturally maskable or
+ * shadowable for guests but this is not (currently) the case.
+ * Takes the guest view of SPEC_CTRL MSR as a parameter.
+ */
+extern void x86_spec_ctrl_set_guest(u64);
+extern void x86_spec_ctrl_restore_host(u64);
+
 extern char __indirect_thunk_start[];
 extern char __indirect_thunk_end[];
 
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 42c2204..e71e281 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -122,6 +122,24 @@ u64 x86_spec_ctrl_get_default(void)
 }
 EXPORT_SYMBOL_GPL(x86_spec_ctrl_get_default);
 
+void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl)
+{
+	if (!boot_cpu_has(X86_FEATURE_IBRS))
+		return;
+	if (x86_spec_ctrl_base != guest_spec_ctrl)
+		wrmsrl(MSR_IA32_SPEC_CTRL, guest_spec_ctrl);
+}
+EXPORT_SYMBOL_GPL(x86_spec_ctrl_set_guest);
+
+void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl)
+{
+	if (!boot_cpu_has(X86_FEATURE_IBRS))
+		return;
+	if (x86_spec_ctrl_base != guest_spec_ctrl)
+		wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+}
+EXPORT_SYMBOL_GPL(x86_spec_ctrl_restore_host);
+
 #ifdef RETPOLINE
 static bool spectre_v2_bad_module;
 

[PATCH 4.4.y 057/101] x86/cpu: Rename Merrifield2 to Moorefield

[Srivatsa S. Bhat]

From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>

commit f5fbf848303c8704d0e1a1e7cabd08fd0a49552f upstream

Merrifield2 is actually Moorefield.

Rename it accordingly and drop tail digit from Merrifield1.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20160906184254.94440-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/intel-family.h |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 12fa187..0b27c1e 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -58,8 +58,8 @@
 #define INTEL_FAM6_ATOM_SILVERMONT1	0x37 /* BayTrail/BYT / Valleyview */
 #define INTEL_FAM6_ATOM_SILVERMONT2	0x4D /* Avaton/Rangely */
 #define INTEL_FAM6_ATOM_AIRMONT		0x4C /* CherryTrail / Braswell */
-#define INTEL_FAM6_ATOM_MERRIFIELD1	0x4A /* Tangier */
-#define INTEL_FAM6_ATOM_MERRIFIELD2	0x5A /* Annidale */
+#define INTEL_FAM6_ATOM_MERRIFIELD	0x4A /* Tangier */
+#define INTEL_FAM6_ATOM_MOOREFIELD	0x5A /* Annidale */
 #define INTEL_FAM6_ATOM_GOLDMONT	0x5C
 #define INTEL_FAM6_ATOM_DENVERTON	0x5F /* Goldmont Microserver */
 #define INTEL_FAM6_ATOM_GEMINI_LAKE	0x7A

[PATCH 4.4.y 058/101] x86/cpu/intel: Add Knights Mill to Intel family

[Srivatsa S. Bhat]

From: Piotr Luc <piotr.luc@intel.com>

commit 0047f59834e5947d45f34f5f12eb330d158f700b upstream

Add CPUID of Knights Mill (KNM) processor to Intel family list.

Signed-off-by: Piotr Luc <piotr.luc@intel.com>
Reviewed-by: Dave Hansen <dave.hansen@intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20161012180520.30976-1-piotr.luc@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/intel-family.h |    1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 0b27c1e..e13ff5a 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -67,5 +67,6 @@
 /* Xeon Phi */
 
 #define INTEL_FAM6_XEON_PHI_KNL		0x57 /* Knights Landing */
+#define INTEL_FAM6_XEON_PHI_KNM		0x85 /* Knights Mill */
 
 #endif /* _ASM_X86_INTEL_FAMILY_H */

[PATCH 4.4.y 059/101] x86/bugs: Expose /sys/../spec_store_bypass

[Srivatsa S. Bhat]

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

commit c456442cd3a59eeb1d60293c26cbe2ff2c4e42cf upstream

Add the sysfs file for the new vulerability. It does not do much except
show the words 'Vulnerable' for recent x86 cores.

Intel cores prior to family 6 are known not to be vulnerable, and so are
some Atoms and some Xeon Phi.

It assumes that older Cyrix, Centaur, etc. cores are immune.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 Documentation/ABI/testing/sysfs-devices-system-cpu |    1 +
 arch/x86/include/asm/cpufeatures.h                 |    1 +
 arch/x86/kernel/cpu/bugs.c                         |    5 ++++
 arch/x86/kernel/cpu/common.c                       |   23 ++++++++++++++++++++
 drivers/base/cpu.c                                 |    8 +++++++
 include/linux/cpu.h                                |    2 ++
 6 files changed, 40 insertions(+)

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index ea6a043..50f9568 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -276,6 +276,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/meltdown
 		/sys/devices/system/cpu/vulnerabilities/spectre_v1
 		/sys/devices/system/cpu/vulnerabilities/spectre_v2
+		/sys/devices/system/cpu/vulnerabilities/spec_store_bypass
 Date:		January 2018
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	Information about CPU vulnerabilities
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index bc76bf3..08cf4f7 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -315,5 +315,6 @@
 #define X86_BUG_CPU_MELTDOWN	X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
 #define X86_BUG_SPECTRE_V1	X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
 #define X86_BUG_SPECTRE_V2	X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
+#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index e71e281..0ad13b1 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -403,4 +403,9 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V2);
 }
+
+ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS);
+}
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 97558d1..eb78ddf 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -835,10 +835,33 @@ static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
 	{}
 };
 
+static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_PINEVIEW	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_LINCROFT	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_PENWELL		},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_CLOVERVIEW	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_CEDARVIEW	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT1	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT2	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_MERRIFIELD	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_CORE_YONAH		},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNL		},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNM		},
+	{ X86_VENDOR_CENTAUR,	5,					},
+	{ X86_VENDOR_INTEL,	5,					},
+	{ X86_VENDOR_NSC,	5,					},
+	{ X86_VENDOR_ANY,	4,					},
+	{}
+};
+
 static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 ia32_cap = 0;
 
+	if (!x86_match_cpu(cpu_no_spec_store_bypass))
+		setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
+
 	if (x86_match_cpu(cpu_no_speculation))
 		return;
 
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 3db71af..143edea 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -518,14 +518,22 @@ ssize_t __weak cpu_show_spectre_v2(struct device *dev,
 	return sprintf(buf, "Not affected\n");
 }
 
+ssize_t __weak cpu_show_spec_store_bypass(struct device *dev,
+					  struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Not affected\n");
+}
+
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
 static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
+static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
 	&dev_attr_spectre_v1.attr,
 	&dev_attr_spectre_v2.attr,
+	&dev_attr_spec_store_bypass.attr,
 	NULL
 };
 
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 7e04bcd..2f9d120 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -46,6 +46,8 @@ extern ssize_t cpu_show_spectre_v1(struct device *dev,
 				   struct device_attribute *attr, char *buf);
 extern ssize_t cpu_show_spectre_v2(struct device *dev,
 				   struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_spec_store_bypass(struct device *dev,
+					  struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,

[PATCH 4.4.y 060/101] x86/cpufeatures: Add X86_FEATURE_RDS

[Srivatsa S. Bhat]

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

commit 0cc5fa00b0a88dad140b4e5c2cead9951ad36822 upstream

Add the CPU feature bit CPUID.7.0.EDX[31] which indicates whether the CPU
supports Reduced Data Speculation.

[ tglx: Split it out from a later patch ]

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeatures.h |    1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 08cf4f7..3fce65d 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -297,6 +297,7 @@
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
+#define X86_FEATURE_RDS			(18*32+31) /* Reduced Data Speculation */
 
 /*
  * BUG word(s)

[PATCH 4.4.y 061/101] x86/bugs: Provide boot parameters for the spec_store_bypass_disable mitigation

[Srivatsa S. Bhat]

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

commit 24f7fc83b9204d20f878c57cb77d261ae825e033 upstream

Contemporary high performance processors use a common industry-wide
optimization known as "Speculative Store Bypass" in which loads from
addresses to which a recent store has occurred may (speculatively) see an
older value. Intel refers to this feature as "Memory Disambiguation" which
is part of their "Smart Memory Access" capability.

Memory Disambiguation can expose a cache side-channel attack against such
speculatively read values. An attacker can create exploit code that allows
them to read memory outside of a sandbox environment (for example,
malicious JavaScript in a web page), or to perform more complex attacks
against code running within the same privilege level, e.g. via the stack.

As a first step to mitigate against such attacks, provide two boot command
line control knobs:

 nospec_store_bypass_disable
 spec_store_bypass_disable=[off,auto,on]

By default affected x86 processors will power on with Speculative
Store Bypass enabled. Hence the provided kernel parameters are written
from the point of view of whether to enable a mitigation or not.
The parameters are as follows:

 - auto - Kernel detects whether your CPU model contains an implementation
	  of Speculative Store Bypass and picks the most appropriate
	  mitigation.

 - on   - disable Speculative Store Bypass
 - off  - enable Speculative Store Bypass

[ tglx: Reordered the checks so that the whole evaluation is not done
  	when the CPU does not support RDS ]

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 Documentation/kernel-parameters.txt  |   33 +++++++++++
 arch/x86/include/asm/cpufeatures.h   |    1 
 arch/x86/include/asm/nospec-branch.h |    6 ++
 arch/x86/kernel/cpu/bugs.c           |  103 ++++++++++++++++++++++++++++++++++
 4 files changed, 143 insertions(+)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index e60d0b5..dc138b8 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2460,6 +2460,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			allow data leaks with this option, which is equivalent
 			to spectre_v2=off.
 
+	nospec_store_bypass_disable
+			[HW] Disable all mitigations for the Speculative Store Bypass vulnerability
+
 	noxsave		[BUGS=X86] Disables x86 extended register state save
 			and restore using xsave. The kernel will fallback to
 			enabling legacy floating-point and sse state.
@@ -3623,6 +3626,36 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Not specifying this option is equivalent to
 			spectre_v2=auto.
 
+	spec_store_bypass_disable=
+			[HW] Control Speculative Store Bypass (SSB) Disable mitigation
+			(Speculative Store Bypass vulnerability)
+
+			Certain CPUs are vulnerable to an exploit against a
+			a common industry wide performance optimization known
+			as "Speculative Store Bypass" in which recent stores
+			to the same memory location may not be observed by
+			later loads during speculative execution. The idea
+			is that such stores are unlikely and that they can
+			be detected prior to instruction retirement at the
+			end of a particular speculation execution window.
+
+			In vulnerable processors, the speculatively forwarded
+			store can be used in a cache side channel attack, for
+			example to read memory to which the attacker does not
+			directly have access (e.g. inside sandboxed code).
+
+			This parameter controls whether the Speculative Store
+			Bypass optimization is used.
+
+			on     - Unconditionally disable Speculative Store Bypass
+			off    - Unconditionally enable Speculative Store Bypass
+			auto   - Kernel detects whether the CPU model contains an
+				 implementation of Speculative Store Bypass and
+				 picks the most appropriate mitigation
+
+			Not specifying this option is equivalent to
+			spec_store_bypass_disable=auto.
+
 	spia_io_base=	[HW,MTD]
 	spia_fio_base=
 	spia_pedr=
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 3fce65d..9510f5f 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -203,6 +203,7 @@
 
 #define X86_FEATURE_USE_IBPB	( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled*/
 #define X86_FEATURE_USE_IBRS_FW	( 7*32+22) /* "" Use IBRS during runtime firmware calls */
+#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE	( 7*32+23) /* "" Disable Speculative Store Bypass. */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 11db69a..c786d01 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -193,6 +193,12 @@ extern u64 x86_spec_ctrl_get_default(void);
 extern void x86_spec_ctrl_set_guest(u64);
 extern void x86_spec_ctrl_restore_host(u64);
 
+/* The Speculative Store Bypass disable variants */
+enum ssb_mitigation {
+	SPEC_STORE_BYPASS_NONE,
+	SPEC_STORE_BYPASS_DISABLE,
+};
+
 extern char __indirect_thunk_start[];
 extern char __indirect_thunk_end[];
 
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 0ad13b1..826aa81 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -26,6 +26,7 @@
 #include <asm/intel-family.h>
 
 static void __init spectre_v2_select_mitigation(void);
+static void __init ssb_select_mitigation(void);
 
 /*
  * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any
@@ -52,6 +53,12 @@ void __init check_bugs(void)
 	/* Select the proper spectre mitigation before patching alternatives */
 	spectre_v2_select_mitigation();
 
+	/*
+	 * Select proper mitigation for any exposure to the Speculative Store
+	 * Bypass vulnerability.
+	 */
+	ssb_select_mitigation();
+
 #ifdef CONFIG_X86_32
 	/*
 	 * Check whether we are able to run this kernel safely on SMP.
@@ -357,6 +364,99 @@ retpoline_auto:
 }
 
 #undef pr_fmt
+#define pr_fmt(fmt)	"Speculative Store Bypass: " fmt
+
+static enum ssb_mitigation ssb_mode = SPEC_STORE_BYPASS_NONE;
+
+/* The kernel command line selection */
+enum ssb_mitigation_cmd {
+	SPEC_STORE_BYPASS_CMD_NONE,
+	SPEC_STORE_BYPASS_CMD_AUTO,
+	SPEC_STORE_BYPASS_CMD_ON,
+};
+
+static const char *ssb_strings[] = {
+	[SPEC_STORE_BYPASS_NONE]	= "Vulnerable",
+	[SPEC_STORE_BYPASS_DISABLE]	= "Mitigation: Speculative Store Bypass disabled"
+};
+
+static const struct {
+	const char *option;
+	enum ssb_mitigation_cmd cmd;
+} ssb_mitigation_options[] = {
+	{ "auto",	SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */
+	{ "on",		SPEC_STORE_BYPASS_CMD_ON },   /* Disable Speculative Store Bypass */
+	{ "off",	SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */
+};
+
+static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void)
+{
+	enum ssb_mitigation_cmd cmd = SPEC_STORE_BYPASS_CMD_AUTO;
+	char arg[20];
+	int ret, i;
+
+	if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) {
+		return SPEC_STORE_BYPASS_CMD_NONE;
+	} else {
+		ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable",
+					  arg, sizeof(arg));
+		if (ret < 0)
+			return SPEC_STORE_BYPASS_CMD_AUTO;
+
+		for (i = 0; i < ARRAY_SIZE(ssb_mitigation_options); i++) {
+			if (!match_option(arg, ret, ssb_mitigation_options[i].option))
+				continue;
+
+			cmd = ssb_mitigation_options[i].cmd;
+			break;
+		}
+
+		if (i >= ARRAY_SIZE(ssb_mitigation_options)) {
+			pr_err("unknown option (%s). Switching to AUTO select\n", arg);
+			return SPEC_STORE_BYPASS_CMD_AUTO;
+		}
+	}
+
+	return cmd;
+}
+
+static enum ssb_mitigation_cmd __init __ssb_select_mitigation(void)
+{
+	enum ssb_mitigation mode = SPEC_STORE_BYPASS_NONE;
+	enum ssb_mitigation_cmd cmd;
+
+	if (!boot_cpu_has(X86_FEATURE_RDS))
+		return mode;
+
+	cmd = ssb_parse_cmdline();
+	if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS) &&
+	    (cmd == SPEC_STORE_BYPASS_CMD_NONE ||
+	     cmd == SPEC_STORE_BYPASS_CMD_AUTO))
+		return mode;
+
+	switch (cmd) {
+	case SPEC_STORE_BYPASS_CMD_AUTO:
+	case SPEC_STORE_BYPASS_CMD_ON:
+		mode = SPEC_STORE_BYPASS_DISABLE;
+		break;
+	case SPEC_STORE_BYPASS_CMD_NONE:
+		break;
+	}
+
+	if (mode != SPEC_STORE_BYPASS_NONE)
+		setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE);
+	return mode;
+}
+
+static void ssb_select_mitigation()
+{
+	ssb_mode = __ssb_select_mitigation();
+
+	if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+		pr_info("%s\n", ssb_strings[ssb_mode]);
+}
+
+#undef pr_fmt
 
 #ifdef CONFIG_SYSFS
 
@@ -382,6 +482,9 @@ ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			       boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
 			       spectre_v2_module_string());
 
+	case X86_BUG_SPEC_STORE_BYPASS:
+		return sprintf(buf, "%s\n", ssb_strings[ssb_mode]);
+
 	default:
 		break;
 	}

[PATCH 4.4.y 062/101] x86/bugs/intel: Set proper CPU features and setup RDS

[Srivatsa S. Bhat]

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

commit 772439717dbf703b39990be58d8d4e3e4ad0598a upstream

Intel CPUs expose methods to:

 - Detect whether RDS capability is available via CPUID.7.0.EDX[31],

 - The SPEC_CTRL MSR(0x48), bit 2 set to enable RDS.

 - MSR_IA32_ARCH_CAPABILITIES, Bit(4) no need to enable RRS.

With that in mind if spec_store_bypass_disable=[auto,on] is selected set at
boot-time the SPEC_CTRL MSR to enable RDS if the platform requires it.

Note that this does not fix the KVM case where the SPEC_CTRL is exposed to
guests which can muck with it, see patch titled :
 KVM/SVM/VMX/x86/spectre_v2: Support the combination of guest and host IBRS.

And for the firmware (IBRS to be set), see patch titled:
 x86/spectre_v2: Read SPEC_CTRL MSR during boot and re-use reserved bits

[ tglx: Distangled it from the intel implementation and kept the call order ]

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/msr-index.h |    6 ++++++
 arch/x86/kernel/cpu/bugs.c       |   30 ++++++++++++++++++++++++++++--
 arch/x86/kernel/cpu/common.c     |   10 ++++++----
 arch/x86/kernel/cpu/cpu.h        |    3 +++
 arch/x86/kernel/cpu/intel.c      |    1 +
 5 files changed, 44 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index f4701f0..a29edb7 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -35,6 +35,7 @@
 #define MSR_IA32_SPEC_CTRL		0x00000048 /* Speculation Control */
 #define SPEC_CTRL_IBRS			(1 << 0)   /* Indirect Branch Restricted Speculation */
 #define SPEC_CTRL_STIBP			(1 << 1)   /* Single Thread Indirect Branch Predictors */
+#define SPEC_CTRL_RDS			(1 << 2)   /* Reduced Data Speculation */
 
 #define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
 #define PRED_CMD_IBPB			(1 << 0)   /* Indirect Branch Prediction Barrier */
@@ -56,6 +57,11 @@
 #define MSR_IA32_ARCH_CAPABILITIES	0x0000010a
 #define ARCH_CAP_RDCL_NO		(1 << 0)   /* Not susceptible to Meltdown */
 #define ARCH_CAP_IBRS_ALL		(1 << 1)   /* Enhanced IBRS support */
+#define ARCH_CAP_RDS_NO			(1 << 4)   /*
+						    * Not susceptible to Speculative Store Bypass
+						    * attack, so no Reduced Data Speculation control
+						    * required.
+						    */
 
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 826aa81..56b84a5 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -116,7 +116,7 @@ static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE;
 
 void x86_spec_ctrl_set(u64 val)
 {
-	if (val & ~SPEC_CTRL_IBRS)
+	if (val & ~(SPEC_CTRL_IBRS | SPEC_CTRL_RDS))
 		WARN_ONCE(1, "SPEC_CTRL MSR value 0x%16llx is unknown.\n", val);
 	else
 		wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base | val);
@@ -443,8 +443,28 @@ static enum ssb_mitigation_cmd __init __ssb_select_mitigation(void)
 		break;
 	}
 
-	if (mode != SPEC_STORE_BYPASS_NONE)
+	/*
+	 * We have three CPU feature flags that are in play here:
+	 *  - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible.
+	 *  - X86_FEATURE_RDS - CPU is able to turn off speculative store bypass
+	 *  - X86_FEATURE_SPEC_STORE_BYPASS_DISABLE - engage the mitigation
+	 */
+	if (mode != SPEC_STORE_BYPASS_NONE) {
 		setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE);
+		/*
+		 * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD uses
+		 * a completely different MSR and bit dependent on family.
+		 */
+		switch (boot_cpu_data.x86_vendor) {
+		case X86_VENDOR_INTEL:
+			x86_spec_ctrl_base |= SPEC_CTRL_RDS;
+			x86_spec_ctrl_set(SPEC_CTRL_RDS);
+			break;
+		case X86_VENDOR_AMD:
+			break;
+		}
+	}
+
 	return mode;
 }
 
@@ -458,6 +478,12 @@ static void ssb_select_mitigation()
 
 #undef pr_fmt
 
+void x86_spec_ctrl_setup_ap(void)
+{
+	if (boot_cpu_has(X86_FEATURE_IBRS))
+		x86_spec_ctrl_set(x86_spec_ctrl_base & (SPEC_CTRL_IBRS | SPEC_CTRL_RDS));
+}
+
 #ifdef CONFIG_SYSFS
 
 ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index eb78ddf..2f1d403 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -859,7 +859,11 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 ia32_cap = 0;
 
-	if (!x86_match_cpu(cpu_no_spec_store_bypass))
+	if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
+		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
+
+	if (!x86_match_cpu(cpu_no_spec_store_bypass) &&
+	   !(ia32_cap & ARCH_CAP_RDS_NO))
 		setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
 
 	if (x86_match_cpu(cpu_no_speculation))
@@ -871,9 +875,6 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	if (x86_match_cpu(cpu_no_meltdown))
 		return;
 
-	if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
-		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
-
 	/* Rogue Data Cache Load? No! */
 	if (ia32_cap & ARCH_CAP_RDCL_NO)
 		return;
@@ -1216,6 +1217,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
 	enable_sep_cpu();
 #endif
 	mtrr_ap_init();
+	x86_spec_ctrl_setup_ap();
 }
 
 struct msr_range {
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 2584265..3b19d82 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -46,4 +46,7 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[],
 
 extern void get_cpu_cap(struct cpuinfo_x86 *c);
 extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
+
+extern void x86_spec_ctrl_setup_ap(void);
+
 #endif /* ARCH_X86_CPU_H */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 77d9f68..ac25d1e5 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -119,6 +119,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		setup_clear_cpu_cap(X86_FEATURE_STIBP);
 		setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL);
 		setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP);
+		setup_clear_cpu_cap(X86_FEATURE_RDS);
 	}
 
 	/*

[PATCH 4.4.y 063/101] x86/bugs: Whitelist allowed SPEC_CTRL MSR values

[Srivatsa S. Bhat]

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

commit 1115a859f33276fe8afb31c60cf9d8e657872558 upstream

Intel and AMD SPEC_CTRL (0x48) MSR semantics may differ in the
future (or in fact use different MSRs for the same functionality).

As such a run-time mechanism is required to whitelist the appropriate MSR
values.

[ tglx: Made the variable __ro_after_init ]
[ Srivatsa: Removed __ro_after_init for 4.4.y ]

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/bugs.c |   11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 56b84a5..c37e211 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -34,6 +34,12 @@ static void __init ssb_select_mitigation(void);
  */
 static u64 x86_spec_ctrl_base;
 
+/*
+ * The vendor and possibly platform specific bits which can be modified in
+ * x86_spec_ctrl_base.
+ */
+static u64 x86_spec_ctrl_mask = ~SPEC_CTRL_IBRS;
+
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
@@ -116,7 +122,7 @@ static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE;
 
 void x86_spec_ctrl_set(u64 val)
 {
-	if (val & ~(SPEC_CTRL_IBRS | SPEC_CTRL_RDS))
+	if (val & x86_spec_ctrl_mask)
 		WARN_ONCE(1, "SPEC_CTRL MSR value 0x%16llx is unknown.\n", val);
 	else
 		wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base | val);
@@ -458,6 +464,7 @@ static enum ssb_mitigation_cmd __init __ssb_select_mitigation(void)
 		switch (boot_cpu_data.x86_vendor) {
 		case X86_VENDOR_INTEL:
 			x86_spec_ctrl_base |= SPEC_CTRL_RDS;
+			x86_spec_ctrl_mask &= ~SPEC_CTRL_RDS;
 			x86_spec_ctrl_set(SPEC_CTRL_RDS);
 			break;
 		case X86_VENDOR_AMD:
@@ -481,7 +488,7 @@ static void ssb_select_mitigation()
 void x86_spec_ctrl_setup_ap(void)
 {
 	if (boot_cpu_has(X86_FEATURE_IBRS))
-		x86_spec_ctrl_set(x86_spec_ctrl_base & (SPEC_CTRL_IBRS | SPEC_CTRL_RDS));
+		x86_spec_ctrl_set(x86_spec_ctrl_base & ~x86_spec_ctrl_mask);
 }
 
 #ifdef CONFIG_SYSFS

[PATCH 4.4.y 064/101] x86/bugs/AMD: Add support to disable RDS on Fam[15, 16, 17]h if requested

[Srivatsa S. Bhat]

From: David Woodhouse <dwmw@amazon.co.uk>

commit 764f3c21588a059cd783c6ba0734d4db2d72822d upstream

AMD does not need the Speculative Store Bypass mitigation to be enabled.

The parameters for this are already available and can be done via MSR
C001_1020. Each family uses a different bit in that MSR for this.

[ tglx: Expose the bit mask via a variable and move the actual MSR fiddling
  	into the bugs code as that's the right thing to do and also required
	to prepare for dynamic enable/disable ]

[ Srivatsa: Removed __ro_after_init for 4.4.y ]

Suggested-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeatures.h   |    1 +
 arch/x86/include/asm/nospec-branch.h |    4 ++++
 arch/x86/kernel/cpu/amd.c            |   26 ++++++++++++++++++++++++++
 arch/x86/kernel/cpu/bugs.c           |   27 ++++++++++++++++++++++++++-
 arch/x86/kernel/cpu/common.c         |    4 ++++
 5 files changed, 61 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 9510f5f..b7cdd1c 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -204,6 +204,7 @@
 #define X86_FEATURE_USE_IBPB	( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled*/
 #define X86_FEATURE_USE_IBRS_FW	( 7*32+22) /* "" Use IBRS during runtime firmware calls */
 #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE	( 7*32+23) /* "" Disable Speculative Store Bypass. */
+#define X86_FEATURE_AMD_RDS	(7*32+24)  /* "" AMD RDS implementation */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index c786d01..ac2fdc96 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -199,6 +199,10 @@ enum ssb_mitigation {
 	SPEC_STORE_BYPASS_DISABLE,
 };
 
+/* AMD specific Speculative Store Bypass MSR data */
+extern u64 x86_amd_ls_cfg_base;
+extern u64 x86_amd_ls_cfg_rds_mask;
+
 extern char __indirect_thunk_start[];
 extern char __indirect_thunk_end[];
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 9b29414..4452f38 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -9,6 +9,7 @@
 #include <asm/processor.h>
 #include <asm/apic.h>
 #include <asm/cpu.h>
+#include <asm/nospec-branch.h>
 #include <asm/smp.h>
 #include <asm/pci-direct.h>
 #include <asm/delay.h>
@@ -519,6 +520,26 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 
 	if (cpu_has(c, X86_FEATURE_MWAITX))
 		use_mwaitx_delay();
+
+	if (c->x86 >= 0x15 && c->x86 <= 0x17) {
+		unsigned int bit;
+
+		switch (c->x86) {
+		case 0x15: bit = 54; break;
+		case 0x16: bit = 33; break;
+		case 0x17: bit = 10; break;
+		default: return;
+		}
+		/*
+		 * Try to cache the base value so further operations can
+		 * avoid RMW. If that faults, do not enable RDS.
+		 */
+		if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
+			setup_force_cpu_cap(X86_FEATURE_RDS);
+			setup_force_cpu_cap(X86_FEATURE_AMD_RDS);
+			x86_amd_ls_cfg_rds_mask = 1ULL << bit;
+		}
+	}
 }
 
 static void early_init_amd(struct cpuinfo_x86 *c)
@@ -794,6 +815,11 @@ static void init_amd(struct cpuinfo_x86 *c)
 	/* AMD CPUs don't reset SS attributes on SYSRET, Xen does. */
 	if (!cpu_has(c, X86_FEATURE_XENPV))
 		set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+
+	if (boot_cpu_has(X86_FEATURE_AMD_RDS)) {
+		set_cpu_cap(c, X86_FEATURE_RDS);
+		set_cpu_cap(c, X86_FEATURE_AMD_RDS);
+	}
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index c37e211..b8911af 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -40,6 +40,13 @@ static u64 x86_spec_ctrl_base;
  */
 static u64 x86_spec_ctrl_mask = ~SPEC_CTRL_IBRS;
 
+/*
+ * AMD specific MSR info for Speculative Store Bypass control.
+ * x86_amd_ls_cfg_rds_mask is initialized in identify_boot_cpu().
+ */
+u64 x86_amd_ls_cfg_base;
+u64 x86_amd_ls_cfg_rds_mask;
+
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
@@ -51,7 +58,8 @@ void __init check_bugs(void)
 
 	/*
 	 * Read the SPEC_CTRL MSR to account for reserved bits which may
-	 * have unknown values.
+	 * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD
+	 * init code as it is not enumerated and depends on the family.
 	 */
 	if (boot_cpu_has(X86_FEATURE_IBRS))
 		rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
@@ -153,6 +161,14 @@ void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl)
 }
 EXPORT_SYMBOL_GPL(x86_spec_ctrl_restore_host);
 
+static void x86_amd_rds_enable(void)
+{
+	u64 msrval = x86_amd_ls_cfg_base | x86_amd_ls_cfg_rds_mask;
+
+	if (boot_cpu_has(X86_FEATURE_AMD_RDS))
+		wrmsrl(MSR_AMD64_LS_CFG, msrval);
+}
+
 #ifdef RETPOLINE
 static bool spectre_v2_bad_module;
 
@@ -442,6 +458,11 @@ static enum ssb_mitigation_cmd __init __ssb_select_mitigation(void)
 
 	switch (cmd) {
 	case SPEC_STORE_BYPASS_CMD_AUTO:
+		/*
+		 * AMD platforms by default don't need SSB mitigation.
+		 */
+		if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+			break;
 	case SPEC_STORE_BYPASS_CMD_ON:
 		mode = SPEC_STORE_BYPASS_DISABLE;
 		break;
@@ -468,6 +489,7 @@ static enum ssb_mitigation_cmd __init __ssb_select_mitigation(void)
 			x86_spec_ctrl_set(SPEC_CTRL_RDS);
 			break;
 		case X86_VENDOR_AMD:
+			x86_amd_rds_enable();
 			break;
 		}
 	}
@@ -489,6 +511,9 @@ void x86_spec_ctrl_setup_ap(void)
 {
 	if (boot_cpu_has(X86_FEATURE_IBRS))
 		x86_spec_ctrl_set(x86_spec_ctrl_base & ~x86_spec_ctrl_mask);
+
+	if (ssb_mode == SPEC_STORE_BYPASS_DISABLE)
+		x86_amd_rds_enable();
 }
 
 #ifdef CONFIG_SYSFS
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 2f1d403..7405c86 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -851,6 +851,10 @@ static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
 	{ X86_VENDOR_CENTAUR,	5,					},
 	{ X86_VENDOR_INTEL,	5,					},
 	{ X86_VENDOR_NSC,	5,					},
+	{ X86_VENDOR_AMD,	0x12,					},
+	{ X86_VENDOR_AMD,	0x11,					},
+	{ X86_VENDOR_AMD,	0x10,					},
+	{ X86_VENDOR_AMD,	0xf,					},
 	{ X86_VENDOR_ANY,	4,					},
 	{}
 };

[PATCH 4.4.y 065/101] x86/speculation: Create spec-ctrl.h to avoid include hell

[Srivatsa S. Bhat]

From: Thomas Gleixner <tglx@linutronix.de>

commit 28a2775217b17208811fa43a9e96bd1fdf417b86 upstream

Having everything in nospec-branch.h creates a hell of dependencies when
adding the prctl based switching mechanism. Move everything which is not
required in nospec-branch.h to spec-ctrl.h and fix up the includes in the
relevant files.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/nospec-branch.h |   14 --------------
 arch/x86/include/asm/spec-ctrl.h     |   21 +++++++++++++++++++++
 arch/x86/kernel/cpu/amd.c            |    2 +-
 arch/x86/kernel/cpu/bugs.c           |    2 +-
 arch/x86/kvm/svm.c                   |    2 +-
 arch/x86/kvm/vmx.c                   |    2 +-
 6 files changed, 25 insertions(+), 18 deletions(-)
 create mode 100644 arch/x86/include/asm/spec-ctrl.h

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index ac2fdc96..47c454c 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -183,26 +183,12 @@ enum spectre_v2_mitigation {
 extern void x86_spec_ctrl_set(u64);
 extern u64 x86_spec_ctrl_get_default(void);
 
-/*
- * On VMENTER we must preserve whatever view of the SPEC_CTRL MSR
- * the guest has, while on VMEXIT we restore the host view. This
- * would be easier if SPEC_CTRL were architecturally maskable or
- * shadowable for guests but this is not (currently) the case.
- * Takes the guest view of SPEC_CTRL MSR as a parameter.
- */
-extern void x86_spec_ctrl_set_guest(u64);
-extern void x86_spec_ctrl_restore_host(u64);
-
 /* The Speculative Store Bypass disable variants */
 enum ssb_mitigation {
 	SPEC_STORE_BYPASS_NONE,
 	SPEC_STORE_BYPASS_DISABLE,
 };
 
-/* AMD specific Speculative Store Bypass MSR data */
-extern u64 x86_amd_ls_cfg_base;
-extern u64 x86_amd_ls_cfg_rds_mask;
-
 extern char __indirect_thunk_start[];
 extern char __indirect_thunk_end[];
 
diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
new file mode 100644
index 0000000..3ad6442
--- /dev/null
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_SPECCTRL_H_
+#define _ASM_X86_SPECCTRL_H_
+
+#include <asm/nospec-branch.h>
+
+/*
+ * On VMENTER we must preserve whatever view of the SPEC_CTRL MSR
+ * the guest has, while on VMEXIT we restore the host view. This
+ * would be easier if SPEC_CTRL were architecturally maskable or
+ * shadowable for guests but this is not (currently) the case.
+ * Takes the guest view of SPEC_CTRL MSR as a parameter.
+ */
+extern void x86_spec_ctrl_set_guest(u64);
+extern void x86_spec_ctrl_restore_host(u64);
+
+/* AMD specific Speculative Store Bypass MSR data */
+extern u64 x86_amd_ls_cfg_base;
+extern u64 x86_amd_ls_cfg_rds_mask;
+
+#endif
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 4452f38..14e9849 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -9,7 +9,7 @@
 #include <asm/processor.h>
 #include <asm/apic.h>
 #include <asm/cpu.h>
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
 #include <asm/smp.h>
 #include <asm/pci-direct.h>
 #include <asm/delay.h>
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index b8911af..47a3cc0 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -12,7 +12,7 @@
 #include <linux/cpu.h>
 #include <linux/module.h>
 
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
 #include <asm/cmdline.h>
 #include <asm/bugs.h>
 #include <asm/processor.h>
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 4265437..df7827a 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -37,7 +37,7 @@
 #include <asm/desc.h>
 #include <asm/debugreg.h>
 #include <asm/kvm_para.h>
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
 
 #include <asm/virtext.h>
 #include "trace.h"
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 63c44a9..1814388 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -48,7 +48,7 @@
 #include <asm/kexec.h>
 #include <asm/apic.h>
 #include <asm/irq_remapping.h>
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
 
 #include "trace.h"
 #include "pmu.h"

[PATCH 4.4.y 066/101] prctl: Add speculation control prctls

[Srivatsa S. Bhat]

From: Thomas Gleixner <tglx@linutronix.de>

commit b617cfc858161140d69cc0b5cc211996b557a1c7 upstream

Add two new prctls to control aspects of speculation related vulnerabilites
and their mitigations to provide finer grained control over performance
impacting mitigations.

PR_GET_SPECULATION_CTRL returns the state of the speculation misfeature
which is selected with arg2 of prctl(2). The return value uses bit 0-2 with
the following meaning:

Bit  Define           Description
0    PR_SPEC_PRCTL    Mitigation can be controlled per task by
                      PR_SET_SPECULATION_CTRL
1    PR_SPEC_ENABLE   The speculation feature is enabled, mitigation is
                      disabled
2    PR_SPEC_DISABLE  The speculation feature is disabled, mitigation is
                      enabled

If all bits are 0 the CPU is not affected by the speculation misfeature.

If PR_SPEC_PRCTL is set, then the per task control of the mitigation is
available. If not set, prctl(PR_SET_SPECULATION_CTRL) for the speculation
misfeature will fail.

PR_SET_SPECULATION_CTRL allows to control the speculation misfeature, which
is selected by arg2 of prctl(2) per task. arg3 is used to hand in the
control value, i.e. either PR_SPEC_ENABLE or PR_SPEC_DISABLE.

The common return values are:

EINVAL  prctl is not implemented by the architecture or the unused prctl()
        arguments are not 0
ENODEV  arg2 is selecting a not supported speculation misfeature

PR_SET_SPECULATION_CTRL has these additional return values:

ERANGE  arg3 is incorrect, i.e. it's not either PR_SPEC_ENABLE or PR_SPEC_DISABLE
ENXIO   prctl control of the selected speculation misfeature is disabled

The first supported controlable speculation misfeature is
PR_SPEC_STORE_BYPASS. Add the define so this can be shared between
architectures.

Based on an initial patch from Tim Chen and mostly rewritten.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 Documentation/spec_ctrl.txt |   86 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/nospec.h      |    5 +++
 include/uapi/linux/prctl.h  |   11 ++++++
 kernel/sys.c                |   20 ++++++++++
 4 files changed, 122 insertions(+)
 create mode 100644 Documentation/spec_ctrl.txt

diff --git a/Documentation/spec_ctrl.txt b/Documentation/spec_ctrl.txt
new file mode 100644
index 0000000..ddbebcd
--- /dev/null
+++ b/Documentation/spec_ctrl.txt
@@ -0,0 +1,86 @@
+===================
+Speculation Control
+===================
+
+Quite some CPUs have speculation related misfeatures which are in fact
+vulnerabilites causing data leaks in various forms even accross privilege
+domains.
+
+The kernel provides mitigation for such vulnerabilities in various
+forms. Some of these mitigations are compile time configurable and some on
+the kernel command line.
+
+There is also a class of mitigations which are very expensive, but they can
+be restricted to a certain set of processes or tasks in controlled
+environments. The mechanism to control these mitigations is via
+:manpage:`prctl(2)`.
+
+There are two prctl options which are related to this:
+
+ * PR_GET_SPECULATION_CTRL
+
+ * PR_SET_SPECULATION_CTRL
+
+PR_GET_SPECULATION_CTRL
+-----------------------
+
+PR_GET_SPECULATION_CTRL returns the state of the speculation misfeature
+which is selected with arg2 of prctl(2). The return value uses bits 0-2 with
+the following meaning:
+
+==== ================ ===================================================
+Bit  Define           Description
+==== ================ ===================================================
+0    PR_SPEC_PRCTL    Mitigation can be controlled per task by
+                      PR_SET_SPECULATION_CTRL
+1    PR_SPEC_ENABLE   The speculation feature is enabled, mitigation is
+                      disabled
+2    PR_SPEC_DISABLE  The speculation feature is disabled, mitigation is
+                      enabled
+==== ================ ===================================================
+
+If all bits are 0 the CPU is not affected by the speculation misfeature.
+
+If PR_SPEC_PRCTL is set, then the per task control of the mitigation is
+available. If not set, prctl(PR_SET_SPECULATION_CTRL) for the speculation
+misfeature will fail.
+
+PR_SET_SPECULATION_CTRL
+-----------------------
+PR_SET_SPECULATION_CTRL allows to control the speculation misfeature, which
+is selected by arg2 of :manpage:`prctl(2)` per task. arg3 is used to hand
+in the control value, i.e. either PR_SPEC_ENABLE or PR_SPEC_DISABLE.
+
+Common error codes
+------------------
+======= =================================================================
+Value   Meaning
+======= =================================================================
+EINVAL  The prctl is not implemented by the architecture or unused
+        prctl(2) arguments are not 0
+
+ENODEV  arg2 is selecting a not supported speculation misfeature
+======= =================================================================
+
+PR_SET_SPECULATION_CTRL error codes
+-----------------------------------
+======= =================================================================
+Value   Meaning
+======= =================================================================
+0       Success
+
+ERANGE  arg3 is incorrect, i.e. it's neither PR_SPEC_ENABLE nor
+        PR_SPEC_DISABLE
+
+ENXIO   Control of the selected speculation misfeature is not possible.
+        See PR_GET_SPECULATION_CTRL.
+======= =================================================================
+
+Speculation misfeature controls
+-------------------------------
+- PR_SPEC_STORE_BYPASS: Speculative Store Bypass
+
+  Invocations:
+   * prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, 0, 0, 0);
+   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_ENABLE, 0, 0);
+   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE, 0, 0);
diff --git a/include/linux/nospec.h b/include/linux/nospec.h
index e791ebc..700bb8a 100644
--- a/include/linux/nospec.h
+++ b/include/linux/nospec.h
@@ -55,4 +55,9 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
 									\
 	(typeof(_i)) (_i & _mask);					\
 })
+
+/* Speculation control prctl */
+int arch_prctl_spec_ctrl_get(unsigned long which);
+int arch_prctl_spec_ctrl_set(unsigned long which, unsigned long ctrl);
+
 #endif /* _LINUX_NOSPEC_H */
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index a8d0759..3b316be 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -197,4 +197,15 @@ struct prctl_mm_map {
 # define PR_CAP_AMBIENT_LOWER		3
 # define PR_CAP_AMBIENT_CLEAR_ALL	4
 
+/* Per task speculation control */
+#define PR_GET_SPECULATION_CTRL		52
+#define PR_SET_SPECULATION_CTRL		53
+/* Speculation control variants */
+# define PR_SPEC_STORE_BYPASS		0
+/* Return and control values for PR_SET/GET_SPECULATION_CTRL */
+# define PR_SPEC_NOT_AFFECTED		0
+# define PR_SPEC_PRCTL			(1UL << 0)
+# define PR_SPEC_ENABLE			(1UL << 1)
+# define PR_SPEC_DISABLE		(1UL << 2)
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/kernel/sys.c b/kernel/sys.c
index 6624919..d80c33f 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2075,6 +2075,16 @@ static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
 }
 #endif
 
+int __weak arch_prctl_spec_ctrl_get(unsigned long which)
+{
+	return -EINVAL;
+}
+
+int __weak arch_prctl_spec_ctrl_set(unsigned long which, unsigned long ctrl)
+{
+	return -EINVAL;
+}
+
 SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		unsigned long, arg4, unsigned long, arg5)
 {
@@ -2269,6 +2279,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_GET_FP_MODE:
 		error = GET_FP_MODE(me);
 		break;
+	case PR_GET_SPECULATION_CTRL:
+		if (arg3 || arg4 || arg5)
+			return -EINVAL;
+		error = arch_prctl_spec_ctrl_get(arg2);
+		break;
+	case PR_SET_SPECULATION_CTRL:
+		if (arg4 || arg5)
+			return -EINVAL;
+		error = arch_prctl_spec_ctrl_set(arg2, arg3);
+		break;
 	default:
 		error = -EINVAL;
 		break;

[PATCH 4.4.y 067/101] x86/process: Optimize TIF checks in __switch_to_xtra()

[Srivatsa S. Bhat]

From: Kyle Huey <me@kylehuey.com>

commit af8b3cd3934ec60f4c2a420d19a9d416554f140b upstream

Help the compiler to avoid reevaluating the thread flags for each checked
bit by reordering the bit checks and providing an explicit xor for
evaluation.

With default defconfigs for each arch,

x86_64: arch/x86/kernel/process.o
text       data     bss     dec     hex
3056       8577      16   11649    2d81	Before
3024	   8577      16	  11617	   2d61	After

i386: arch/x86/kernel/process.o
text       data     bss     dec     hex
2957	   8673	      8	  11638	   2d76	Before
2925	   8673       8	  11606	   2d56	After

Originally-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Kyle Huey <khuey@kylehuey.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andy Lutomirski <luto@kernel.org>
Link: http://lkml.kernel.org/r/20170214081104.9244-2-khuey@kylehuey.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

[dwmw2: backported to make TIF_RDS handling simpler.
        No deferred TR reload.]
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/process.c |   54 ++++++++++++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 23 deletions(-)

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 7c5c5dc..cc0f288 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -188,48 +188,56 @@ int set_tsc_mode(unsigned int val)
 	return 0;
 }
 
+static inline void switch_to_bitmap(struct tss_struct *tss,
+				    struct thread_struct *prev,
+				    struct thread_struct *next,
+				    unsigned long tifp, unsigned long tifn)
+{
+	if (tifn & _TIF_IO_BITMAP) {
+		/*
+		 * Copy the relevant range of the IO bitmap.
+		 * Normally this is 128 bytes or less:
+		 */
+		memcpy(tss->io_bitmap, next->io_bitmap_ptr,
+		       max(prev->io_bitmap_max, next->io_bitmap_max));
+	} else if (tifp & _TIF_IO_BITMAP) {
+		/*
+		 * Clear any possible leftover bits:
+		 */
+		memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
+	}
+}
+
 void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		      struct tss_struct *tss)
 {
 	struct thread_struct *prev, *next;
+	unsigned long tifp, tifn;
 
 	prev = &prev_p->thread;
 	next = &next_p->thread;
 
-	if (test_tsk_thread_flag(prev_p, TIF_BLOCKSTEP) ^
-	    test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) {
+	tifn = READ_ONCE(task_thread_info(next_p)->flags);
+	tifp = READ_ONCE(task_thread_info(prev_p)->flags);
+	switch_to_bitmap(tss, prev, next, tifp, tifn);
+
+	propagate_user_return_notify(prev_p, next_p);
+
+	if ((tifp ^ tifn) & _TIF_BLOCKSTEP) {
 		unsigned long debugctl = get_debugctlmsr();
 
 		debugctl &= ~DEBUGCTLMSR_BTF;
-		if (test_tsk_thread_flag(next_p, TIF_BLOCKSTEP))
+		if (tifn & _TIF_BLOCKSTEP)
 			debugctl |= DEBUGCTLMSR_BTF;
-
 		update_debugctlmsr(debugctl);
 	}
 
-	if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^
-	    test_tsk_thread_flag(next_p, TIF_NOTSC)) {
-		/* prev and next are different */
-		if (test_tsk_thread_flag(next_p, TIF_NOTSC))
+	if ((tifp ^ tifn) & _TIF_NOTSC) {
+		if (tifn & _TIF_NOTSC)
 			hard_disable_TSC();
 		else
 			hard_enable_TSC();
 	}
-
-	if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) {
-		/*
-		 * Copy the relevant range of the IO bitmap.
-		 * Normally this is 128 bytes or less:
-		 */
-		memcpy(tss->io_bitmap, next->io_bitmap_ptr,
-		       max(prev->io_bitmap_max, next->io_bitmap_max));
-	} else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) {
-		/*
-		 * Clear any possible leftover bits:
-		 */
-		memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
-	}
-	propagate_user_return_notify(prev_p, next_p);
 }
 
 /*

[PATCH 4.4.y 068/101] x86/process: Correct and optimize TIF_BLOCKSTEP switch

[Srivatsa S. Bhat]

From: Kyle Huey <me@kylehuey.com>

commit b9894a2f5bd18b1691cb6872c9afe32b148d0132 upstream

The debug control MSR is "highly magical" as the blockstep bit can be
cleared by hardware under not well documented circumstances.

So a task switch relying on the bit set by the previous task (according to
the previous tasks thread flags) can trip over this and not update the flag
for the next task.

To fix this its required to handle DEBUGCTLMSR_BTF when either the previous
or the next or both tasks have the TIF_BLOCKSTEP flag set.

While at it avoid branching within the TIF_BLOCKSTEP case and evaluating
boot_cpu_data twice in kernels without CONFIG_X86_DEBUGCTLMSR.

x86_64: arch/x86/kernel/process.o
text	data	bss	dec	 hex
3024    8577    16      11617    2d61	Before
3008	8577	16	11601	 2d51	After

i386: No change

[ tglx: Made the shift value explicit, use a local variable to make the
code readable and massaged changelog]

Originally-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Kyle Huey <khuey@kylehuey.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andy Lutomirski <luto@kernel.org>
Link: http://lkml.kernel.org/r/20170214081104.9244-3-khuey@kylehuey.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/msr-index.h |    1 +
 arch/x86/kernel/process.c        |   12 +++++++-----
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index a29edb7..71a2c84 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -150,6 +150,7 @@
 
 /* DEBUGCTLMSR bits (others vary by model): */
 #define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
+#define DEBUGCTLMSR_BTF_SHIFT		1
 #define DEBUGCTLMSR_BTF			(1UL <<  1) /* single-step on branches */
 #define DEBUGCTLMSR_TR			(1UL <<  6)
 #define DEBUGCTLMSR_BTS			(1UL <<  7)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index cc0f288..166aef3 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -223,13 +223,15 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 
 	propagate_user_return_notify(prev_p, next_p);
 
-	if ((tifp ^ tifn) & _TIF_BLOCKSTEP) {
-		unsigned long debugctl = get_debugctlmsr();
+	if ((tifp & _TIF_BLOCKSTEP || tifn & _TIF_BLOCKSTEP) &&
+	    arch_has_block_step()) {
+		unsigned long debugctl, msk;
 
+		rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
 		debugctl &= ~DEBUGCTLMSR_BTF;
-		if (tifn & _TIF_BLOCKSTEP)
-			debugctl |= DEBUGCTLMSR_BTF;
-		update_debugctlmsr(debugctl);
+		msk = tifn & _TIF_BLOCKSTEP;
+		debugctl |= (msk >> TIF_BLOCKSTEP) << DEBUGCTLMSR_BTF_SHIFT;
+		wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
 	}
 
 	if ((tifp ^ tifn) & _TIF_NOTSC) {

[PATCH 4.4.y 069/101] x86/process: Optimize TIF_NOTSC switch

[Srivatsa S. Bhat]

From: Thomas Gleixner <tglx@linutronix.de>

commit 5a920155e388ec22a22e0532fb695b9215c9b34d upstream

Provide and use a toggle helper instead of doing it with a branch.

x86_64: arch/x86/kernel/process.o
text	   data	    bss	    dec	    hex
3008	   8577	     16	  11601	   2d51 Before
2976       8577      16	  11569	   2d31 After

i386: arch/x86/kernel/process.o
text	   data	    bss	    dec	    hex
2925	   8673	      8	  11606	   2d56 Before
2893	   8673       8	  11574	   2d36 After

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andy Lutomirski <luto@kernel.org>
Link: http://lkml.kernel.org/r/20170214081104.9244-4-khuey@kylehuey.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/tlbflush.h |   10 ++++++++++
 arch/x86/kernel/process.c       |   22 ++++------------------
 2 files changed, 14 insertions(+), 18 deletions(-)

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 8ce07db..72cfe3e 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -111,6 +111,16 @@ static inline void cr4_clear_bits(unsigned long mask)
 	}
 }
 
+static inline void cr4_toggle_bits(unsigned long mask)
+{
+	unsigned long cr4;
+
+	cr4 = this_cpu_read(cpu_tlbstate.cr4);
+	cr4 ^= mask;
+	this_cpu_write(cpu_tlbstate.cr4, cr4);
+	__write_cr4(cr4);
+}
+
 /* Read the CR4 shadow. */
 static inline unsigned long cr4_read_shadow(void)
 {
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 166aef3..d112963 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -130,11 +130,6 @@ void flush_thread(void)
 	fpu__clear(&tsk->thread.fpu);
 }
 
-static void hard_disable_TSC(void)
-{
-	cr4_set_bits(X86_CR4_TSD);
-}
-
 void disable_TSC(void)
 {
 	preempt_disable();
@@ -143,15 +138,10 @@ void disable_TSC(void)
 		 * Must flip the CPU state synchronously with
 		 * TIF_NOTSC in the current running context.
 		 */
-		hard_disable_TSC();
+		cr4_set_bits(X86_CR4_TSD);
 	preempt_enable();
 }
 
-static void hard_enable_TSC(void)
-{
-	cr4_clear_bits(X86_CR4_TSD);
-}
-
 static void enable_TSC(void)
 {
 	preempt_disable();
@@ -160,7 +150,7 @@ static void enable_TSC(void)
 		 * Must flip the CPU state synchronously with
 		 * TIF_NOTSC in the current running context.
 		 */
-		hard_enable_TSC();
+		cr4_clear_bits(X86_CR4_TSD);
 	preempt_enable();
 }
 
@@ -234,12 +224,8 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
 	}
 
-	if ((tifp ^ tifn) & _TIF_NOTSC) {
-		if (tifn & _TIF_NOTSC)
-			hard_disable_TSC();
-		else
-			hard_enable_TSC();
-	}
+	if ((tifp ^ tifn) & _TIF_NOTSC)
+		cr4_toggle_bits(X86_CR4_TSD);
 }
 
 /*

[PATCH 4.4.y 070/101] x86/process: Allow runtime control of Speculative Store Bypass

[Srivatsa S. Bhat]

From: Thomas Gleixner <tglx@linutronix.de>

commit 885f82bfbc6fefb6664ea27965c3ab9ac4194b8c upstream

The Speculative Store Bypass vulnerability can be mitigated with the
Reduced Data Speculation (RDS) feature. To allow finer grained control of
this eventually expensive mitigation a per task mitigation control is
required.

Add a new TIF_RDS flag and put it into the group of TIF flags which are
evaluated for mismatch in switch_to(). If these bits differ in the previous
and the next task, then the slow path function __switch_to_xtra() is
invoked. Implement the TIF_RDS dependent mitigation control in the slow
path.

If the prctl for controlling Speculative Store Bypass is disabled or no
task uses the prctl then there is no overhead in the switch_to() fast
path.

Update the KVM related speculation control functions to take TID_RDS into
account as well.

Based on a patch from Tim Chen. Completely rewritten.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/msr-index.h   |    3 ++-
 arch/x86/include/asm/spec-ctrl.h   |   17 +++++++++++++++++
 arch/x86/include/asm/thread_info.h |    6 ++++--
 arch/x86/kernel/cpu/bugs.c         |   26 +++++++++++++++++++++-----
 arch/x86/kernel/process.c          |   22 ++++++++++++++++++++++
 5 files changed, 66 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 71a2c84..883cf0d 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -35,7 +35,8 @@
 #define MSR_IA32_SPEC_CTRL		0x00000048 /* Speculation Control */
 #define SPEC_CTRL_IBRS			(1 << 0)   /* Indirect Branch Restricted Speculation */
 #define SPEC_CTRL_STIBP			(1 << 1)   /* Single Thread Indirect Branch Predictors */
-#define SPEC_CTRL_RDS			(1 << 2)   /* Reduced Data Speculation */
+#define SPEC_CTRL_RDS_SHIFT		2	   /* Reduced Data Speculation bit */
+#define SPEC_CTRL_RDS			(1 << SPEC_CTRL_RDS_SHIFT)   /* Reduced Data Speculation */
 
 #define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
 #define PRED_CMD_IBPB			(1 << 0)   /* Indirect Branch Prediction Barrier */
diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
index 3ad6442..45ef00a 100644
--- a/arch/x86/include/asm/spec-ctrl.h
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -2,6 +2,7 @@
 #ifndef _ASM_X86_SPECCTRL_H_
 #define _ASM_X86_SPECCTRL_H_
 
+#include <linux/thread_info.h>
 #include <asm/nospec-branch.h>
 
 /*
@@ -18,4 +19,20 @@ extern void x86_spec_ctrl_restore_host(u64);
 extern u64 x86_amd_ls_cfg_base;
 extern u64 x86_amd_ls_cfg_rds_mask;
 
+/* The Intel SPEC CTRL MSR base value cache */
+extern u64 x86_spec_ctrl_base;
+
+static inline u64 rds_tif_to_spec_ctrl(u64 tifn)
+{
+	BUILD_BUG_ON(TIF_RDS < SPEC_CTRL_RDS_SHIFT);
+	return (tifn & _TIF_RDS) >> (TIF_RDS - SPEC_CTRL_RDS_SHIFT);
+}
+
+static inline u64 rds_tif_to_amd_ls_cfg(u64 tifn)
+{
+	return (tifn & _TIF_RDS) ? x86_amd_ls_cfg_rds_mask : 0ULL;
+}
+
+extern void speculative_store_bypass_update(void);
+
 #endif
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 18c9aaa..36a49b4 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -92,6 +92,7 @@ struct thread_info {
 #define TIF_SIGPENDING		2	/* signal pending */
 #define TIF_NEED_RESCHED	3	/* rescheduling necessary */
 #define TIF_SINGLESTEP		4	/* reenable singlestep on user return*/
+#define TIF_RDS			5	/* Reduced data speculation */
 #define TIF_SYSCALL_EMU		6	/* syscall emulation active */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SECCOMP		8	/* secure computing */
@@ -114,8 +115,9 @@ struct thread_info {
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
-#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
+#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
+#define _TIF_RDS		(1 << TIF_RDS)
 #define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
@@ -147,7 +149,7 @@ struct thread_info {
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\
-	(_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP)
+	(_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP|_TIF_RDS)
 
 #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 47a3cc0..0f8303e 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -32,7 +32,7 @@ static void __init ssb_select_mitigation(void);
  * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any
  * writes to SPEC_CTRL contain whatever reserved bits have been set.
  */
-static u64 x86_spec_ctrl_base;
+u64 x86_spec_ctrl_base;
 
 /*
  * The vendor and possibly platform specific bits which can be modified in
@@ -139,25 +139,41 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_set);
 
 u64 x86_spec_ctrl_get_default(void)
 {
-	return x86_spec_ctrl_base;
+	u64 msrval = x86_spec_ctrl_base;
+
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		msrval |= rds_tif_to_spec_ctrl(current_thread_info()->flags);
+	return msrval;
 }
 EXPORT_SYMBOL_GPL(x86_spec_ctrl_get_default);
 
 void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl)
 {
+	u64 host = x86_spec_ctrl_base;
+
 	if (!boot_cpu_has(X86_FEATURE_IBRS))
 		return;
-	if (x86_spec_ctrl_base != guest_spec_ctrl)
+
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		host |= rds_tif_to_spec_ctrl(current_thread_info()->flags);
+
+	if (host != guest_spec_ctrl)
 		wrmsrl(MSR_IA32_SPEC_CTRL, guest_spec_ctrl);
 }
 EXPORT_SYMBOL_GPL(x86_spec_ctrl_set_guest);
 
 void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl)
 {
+	u64 host = x86_spec_ctrl_base;
+
 	if (!boot_cpu_has(X86_FEATURE_IBRS))
 		return;
-	if (x86_spec_ctrl_base != guest_spec_ctrl)
-		wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		host |= rds_tif_to_spec_ctrl(current_thread_info()->flags);
+
+	if (host != guest_spec_ctrl)
+		wrmsrl(MSR_IA32_SPEC_CTRL, host);
 }
 EXPORT_SYMBOL_GPL(x86_spec_ctrl_restore_host);
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index d112963..9689e92 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -31,6 +31,7 @@
 #include <asm/tlbflush.h>
 #include <asm/mce.h>
 #include <asm/vm86.h>
+#include <asm/spec-ctrl.h>
 
 /*
  * per-CPU TSS segments. Threads are completely 'soft' on Linux,
@@ -198,6 +199,24 @@ static inline void switch_to_bitmap(struct tss_struct *tss,
 	}
 }
 
+static __always_inline void __speculative_store_bypass_update(unsigned long tifn)
+{
+	u64 msr;
+
+	if (static_cpu_has(X86_FEATURE_AMD_RDS)) {
+		msr = x86_amd_ls_cfg_base | rds_tif_to_amd_ls_cfg(tifn);
+		wrmsrl(MSR_AMD64_LS_CFG, msr);
+	} else {
+		msr = x86_spec_ctrl_base | rds_tif_to_spec_ctrl(tifn);
+		wrmsrl(MSR_IA32_SPEC_CTRL, msr);
+	}
+}
+
+void speculative_store_bypass_update(void)
+{
+	__speculative_store_bypass_update(current_thread_info()->flags);
+}
+
 void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		      struct tss_struct *tss)
 {
@@ -226,6 +245,9 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 
 	if ((tifp ^ tifn) & _TIF_NOTSC)
 		cr4_toggle_bits(X86_CR4_TSD);
+
+	if ((tifp ^ tifn) & _TIF_RDS)
+		__speculative_store_bypass_update(tifn);
 }
 
 /*

[PATCH 4.4.y 071/101] x86/speculation: Add prctl for Speculative Store Bypass mitigation

[Srivatsa S. Bhat]

From: Thomas Gleixner <tglx@linutronix.de>

commit a73ec77ee17ec556fe7f165d00314cb7c047b1ac upstream

Add prctl based control for Speculative Store Bypass mitigation and make it
the default mitigation for Intel and AMD.

Andi Kleen provided the following rationale (slightly redacted):

 There are multiple levels of impact of Speculative Store Bypass:

 1) JITed sandbox.
    It cannot invoke system calls, but can do PRIME+PROBE and may have call
    interfaces to other code

 2) Native code process.
    No protection inside the process at this level.

 3) Kernel.

 4) Between processes.

 The prctl tries to protect against case (1) doing attacks.

 If the untrusted code can do random system calls then control is already
 lost in a much worse way. So there needs to be system call protection in
 some way (using a JIT not allowing them or seccomp). Or rather if the
 process can subvert its environment somehow to do the prctl it can already
 execute arbitrary code, which is much worse than SSB.

 To put it differently, the point of the prctl is to not allow JITed code
 to read data it shouldn't read from its JITed sandbox. If it already has
 escaped its sandbox then it can already read everything it wants in its
 address space, and do much worse.

 The ability to control Speculative Store Bypass allows to enable the
 protection selectively without affecting overall system performance.

Based on an initial patch from Tim Chen. Completely rewritten.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 Documentation/kernel-parameters.txt  |    6 ++
 arch/x86/include/asm/nospec-branch.h |    1 
 arch/x86/kernel/cpu/bugs.c           |   83 ++++++++++++++++++++++++++++++----
 3 files changed, 79 insertions(+), 11 deletions(-)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index dc138b8..80202de 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3651,7 +3651,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			off    - Unconditionally enable Speculative Store Bypass
 			auto   - Kernel detects whether the CPU model contains an
 				 implementation of Speculative Store Bypass and
-				 picks the most appropriate mitigation
+				 picks the most appropriate mitigation.
+			prctl  - Control Speculative Store Bypass per thread
+				 via prctl. Speculative Store Bypass is enabled
+				 for a process by default. The state of the control
+				 is inherited on fork.
 
 			Not specifying this option is equivalent to
 			spec_store_bypass_disable=auto.
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 47c454c..155d955 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -187,6 +187,7 @@ extern u64 x86_spec_ctrl_get_default(void);
 enum ssb_mitigation {
 	SPEC_STORE_BYPASS_NONE,
 	SPEC_STORE_BYPASS_DISABLE,
+	SPEC_STORE_BYPASS_PRCTL,
 };
 
 extern char __indirect_thunk_start[];
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 0f8303e..bcfccd3 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -11,6 +11,8 @@
 #include <linux/utsname.h>
 #include <linux/cpu.h>
 #include <linux/module.h>
+#include <linux/nospec.h>
+#include <linux/prctl.h>
 
 #include <asm/spec-ctrl.h>
 #include <asm/cmdline.h>
@@ -411,20 +413,23 @@ enum ssb_mitigation_cmd {
 	SPEC_STORE_BYPASS_CMD_NONE,
 	SPEC_STORE_BYPASS_CMD_AUTO,
 	SPEC_STORE_BYPASS_CMD_ON,
+	SPEC_STORE_BYPASS_CMD_PRCTL,
 };
 
 static const char *ssb_strings[] = {
 	[SPEC_STORE_BYPASS_NONE]	= "Vulnerable",
-	[SPEC_STORE_BYPASS_DISABLE]	= "Mitigation: Speculative Store Bypass disabled"
+	[SPEC_STORE_BYPASS_DISABLE]	= "Mitigation: Speculative Store Bypass disabled",
+	[SPEC_STORE_BYPASS_PRCTL]	= "Mitigation: Speculative Store Bypass disabled via prctl"
 };
 
 static const struct {
 	const char *option;
 	enum ssb_mitigation_cmd cmd;
 } ssb_mitigation_options[] = {
-	{ "auto",	SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */
-	{ "on",		SPEC_STORE_BYPASS_CMD_ON },   /* Disable Speculative Store Bypass */
-	{ "off",	SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */
+	{ "auto",	SPEC_STORE_BYPASS_CMD_AUTO },  /* Platform decides */
+	{ "on",		SPEC_STORE_BYPASS_CMD_ON },    /* Disable Speculative Store Bypass */
+	{ "off",	SPEC_STORE_BYPASS_CMD_NONE },  /* Don't touch Speculative Store Bypass */
+	{ "prctl",	SPEC_STORE_BYPASS_CMD_PRCTL }, /* Disable Speculative Store Bypass via prctl */
 };
 
 static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void)
@@ -474,14 +479,15 @@ static enum ssb_mitigation_cmd __init __ssb_select_mitigation(void)
 
 	switch (cmd) {
 	case SPEC_STORE_BYPASS_CMD_AUTO:
-		/*
-		 * AMD platforms by default don't need SSB mitigation.
-		 */
-		if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
-			break;
+		/* Choose prctl as the default mode */
+		mode = SPEC_STORE_BYPASS_PRCTL;
+		break;
 	case SPEC_STORE_BYPASS_CMD_ON:
 		mode = SPEC_STORE_BYPASS_DISABLE;
 		break;
+	case SPEC_STORE_BYPASS_CMD_PRCTL:
+		mode = SPEC_STORE_BYPASS_PRCTL;
+		break;
 	case SPEC_STORE_BYPASS_CMD_NONE:
 		break;
 	}
@@ -492,7 +498,7 @@ static enum ssb_mitigation_cmd __init __ssb_select_mitigation(void)
 	 *  - X86_FEATURE_RDS - CPU is able to turn off speculative store bypass
 	 *  - X86_FEATURE_SPEC_STORE_BYPASS_DISABLE - engage the mitigation
 	 */
-	if (mode != SPEC_STORE_BYPASS_NONE) {
+	if (mode == SPEC_STORE_BYPASS_DISABLE) {
 		setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE);
 		/*
 		 * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD uses
@@ -523,6 +529,63 @@ static void ssb_select_mitigation()
 
 #undef pr_fmt
 
+static int ssb_prctl_set(unsigned long ctrl)
+{
+	bool rds = !!test_tsk_thread_flag(current, TIF_RDS);
+
+	if (ssb_mode != SPEC_STORE_BYPASS_PRCTL)
+		return -ENXIO;
+
+	if (ctrl == PR_SPEC_ENABLE)
+		clear_tsk_thread_flag(current, TIF_RDS);
+	else
+		set_tsk_thread_flag(current, TIF_RDS);
+
+	if (rds != !!test_tsk_thread_flag(current, TIF_RDS))
+		speculative_store_bypass_update();
+
+	return 0;
+}
+
+static int ssb_prctl_get(void)
+{
+	switch (ssb_mode) {
+	case SPEC_STORE_BYPASS_DISABLE:
+		return PR_SPEC_DISABLE;
+	case SPEC_STORE_BYPASS_PRCTL:
+		if (test_tsk_thread_flag(current, TIF_RDS))
+			return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
+		return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
+	default:
+		if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+			return PR_SPEC_ENABLE;
+		return PR_SPEC_NOT_AFFECTED;
+	}
+}
+
+int arch_prctl_spec_ctrl_set(unsigned long which, unsigned long ctrl)
+{
+	if (ctrl != PR_SPEC_ENABLE && ctrl != PR_SPEC_DISABLE)
+		return -ERANGE;
+
+	switch (which) {
+	case PR_SPEC_STORE_BYPASS:
+		return ssb_prctl_set(ctrl);
+	default:
+		return -ENODEV;
+	}
+}
+
+int arch_prctl_spec_ctrl_get(unsigned long which)
+{
+	switch (which) {
+	case PR_SPEC_STORE_BYPASS:
+		return ssb_prctl_get();
+	default:
+		return -ENODEV;
+	}
+}
+
 void x86_spec_ctrl_setup_ap(void)
 {
 	if (boot_cpu_has(X86_FEATURE_IBRS))

[PATCH 4.4.y 072/101] nospec: Allow getting/setting on non-current task

[Srivatsa S. Bhat]

From: Kees Cook <keescook@chromium.org>

commit 7bbf1373e228840bb0295a2ca26d548ef37f448e upstream

Adjust arch_prctl_get/set_spec_ctrl() to operate on tasks other than
current.

This is needed both for /proc/$pid/status queries and for seccomp (since
thread-syncing can trigger seccomp in non-current threads).

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/bugs.c |   27 ++++++++++++++++-----------
 include/linux/nospec.h     |    7 +++++--
 kernel/sys.c               |    9 +++++----
 3 files changed, 26 insertions(+), 17 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index bcfccd3..64b54a4 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -529,31 +529,35 @@ static void ssb_select_mitigation()
 
 #undef pr_fmt
 
-static int ssb_prctl_set(unsigned long ctrl)
+static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
 {
-	bool rds = !!test_tsk_thread_flag(current, TIF_RDS);
+	bool rds = !!test_tsk_thread_flag(task, TIF_RDS);
 
 	if (ssb_mode != SPEC_STORE_BYPASS_PRCTL)
 		return -ENXIO;
 
 	if (ctrl == PR_SPEC_ENABLE)
-		clear_tsk_thread_flag(current, TIF_RDS);
+		clear_tsk_thread_flag(task, TIF_RDS);
 	else
-		set_tsk_thread_flag(current, TIF_RDS);
+		set_tsk_thread_flag(task, TIF_RDS);
 
-	if (rds != !!test_tsk_thread_flag(current, TIF_RDS))
+	/*
+	 * If being set on non-current task, delay setting the CPU
+	 * mitigation until it is next scheduled.
+	 */
+	if (task == current && rds != !!test_tsk_thread_flag(task, TIF_RDS))
 		speculative_store_bypass_update();
 
 	return 0;
 }
 
-static int ssb_prctl_get(void)
+static int ssb_prctl_get(struct task_struct *task)
 {
 	switch (ssb_mode) {
 	case SPEC_STORE_BYPASS_DISABLE:
 		return PR_SPEC_DISABLE;
 	case SPEC_STORE_BYPASS_PRCTL:
-		if (test_tsk_thread_flag(current, TIF_RDS))
+		if (test_tsk_thread_flag(task, TIF_RDS))
 			return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
 		return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
 	default:
@@ -563,24 +567,25 @@ static int ssb_prctl_get(void)
 	}
 }
 
-int arch_prctl_spec_ctrl_set(unsigned long which, unsigned long ctrl)
+int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
+			     unsigned long ctrl)
 {
 	if (ctrl != PR_SPEC_ENABLE && ctrl != PR_SPEC_DISABLE)
 		return -ERANGE;
 
 	switch (which) {
 	case PR_SPEC_STORE_BYPASS:
-		return ssb_prctl_set(ctrl);
+		return ssb_prctl_set(task, ctrl);
 	default:
 		return -ENODEV;
 	}
 }
 
-int arch_prctl_spec_ctrl_get(unsigned long which)
+int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
 {
 	switch (which) {
 	case PR_SPEC_STORE_BYPASS:
-		return ssb_prctl_get();
+		return ssb_prctl_get(task);
 	default:
 		return -ENODEV;
 	}
diff --git a/include/linux/nospec.h b/include/linux/nospec.h
index 700bb8a..a908c95 100644
--- a/include/linux/nospec.h
+++ b/include/linux/nospec.h
@@ -7,6 +7,8 @@
 #define _LINUX_NOSPEC_H
 #include <asm/barrier.h>
 
+struct task_struct;
+
 /**
  * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise
  * @index: array element index
@@ -57,7 +59,8 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
 })
 
 /* Speculation control prctl */
-int arch_prctl_spec_ctrl_get(unsigned long which);
-int arch_prctl_spec_ctrl_set(unsigned long which, unsigned long ctrl);
+int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which);
+int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
+			     unsigned long ctrl);
 
 #endif /* _LINUX_NOSPEC_H */
diff --git a/kernel/sys.c b/kernel/sys.c
index d80c33f..f718742 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2075,12 +2075,13 @@ static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
 }
 #endif
 
-int __weak arch_prctl_spec_ctrl_get(unsigned long which)
+int __weak arch_prctl_spec_ctrl_get(struct task_struct *t, unsigned long which)
 {
 	return -EINVAL;
 }
 
-int __weak arch_prctl_spec_ctrl_set(unsigned long which, unsigned long ctrl)
+int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which,
+				    unsigned long ctrl)
 {
 	return -EINVAL;
 }
@@ -2282,12 +2283,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_GET_SPECULATION_CTRL:
 		if (arg3 || arg4 || arg5)
 			return -EINVAL;
-		error = arch_prctl_spec_ctrl_get(arg2);
+		error = arch_prctl_spec_ctrl_get(me, arg2);
 		break;
 	case PR_SET_SPECULATION_CTRL:
 		if (arg4 || arg5)
 			return -EINVAL;
-		error = arch_prctl_spec_ctrl_set(arg2, arg3);
+		error = arch_prctl_spec_ctrl_set(me, arg2, arg3);
 		break;
 	default:
 		error = -EINVAL;

[PATCH 4.4.y 073/101] proc: Provide details on speculation flaw mitigations

[Srivatsa S. Bhat]

From: Kees Cook <keescook@chromium.org>

commit fae1fa0fc6cca8beee3ab8ed71d54f9a78fa3f64 upstream

As done with seccomp and no_new_privs, also show speculation flaw
mitigation state in /proc/$pid/status.

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 fs/proc/array.c |   23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/fs/proc/array.c b/fs/proc/array.c
index b6c00ce..bb48358 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -79,6 +79,7 @@
 #include <linux/delayacct.h>
 #include <linux/seq_file.h>
 #include <linux/pid_namespace.h>
+#include <linux/prctl.h>
 #include <linux/ptrace.h>
 #include <linux/tracehook.h>
 #include <linux/string_helpers.h>
@@ -332,6 +333,28 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p)
 #ifdef CONFIG_SECCOMP
 	seq_printf(m, "Seccomp:\t%d\n", p->seccomp.mode);
 #endif
+	seq_printf(m, "\nSpeculation Store Bypass:\t");
+	switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) {
+	case -EINVAL:
+		seq_printf(m, "unknown");
+		break;
+	case PR_SPEC_NOT_AFFECTED:
+		seq_printf(m, "not vulnerable");
+		break;
+	case PR_SPEC_PRCTL | PR_SPEC_DISABLE:
+		seq_printf(m, "thread mitigated");
+		break;
+	case PR_SPEC_PRCTL | PR_SPEC_ENABLE:
+		seq_printf(m, "thread vulnerable");
+		break;
+	case PR_SPEC_DISABLE:
+		seq_printf(m, "globally mitigated");
+		break;
+	default:
+		seq_printf(m, "vulnerable");
+		break;
+	}
+	seq_putc(m, '\n');
 }
 
 static inline void task_context_switch_counts(struct seq_file *m,

[PATCH 4.4.y 074/101] seccomp: Enable speculation flaw mitigations

[Srivatsa S. Bhat]

From: Kees Cook <keescook@chromium.org>

commit 5c3070890d06ff82eecb808d02d2ca39169533ef upstream

When speculation flaw mitigations are opt-in (via prctl), using seccomp
will automatically opt-in to these protections, since using seccomp
indicates at least some level of sandboxing is desired.

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 kernel/seccomp.c |   17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index efd384f..bfb1ee8 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -16,6 +16,8 @@
 #include <linux/atomic.h>
 #include <linux/audit.h>
 #include <linux/compat.h>
+#include <linux/nospec.h>
+#include <linux/prctl.h>
 #include <linux/sched.h>
 #include <linux/seccomp.h>
 #include <linux/slab.h>
@@ -214,6 +216,19 @@ static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode)
 	return true;
 }
 
+/*
+ * If a given speculation mitigation is opt-in (prctl()-controlled),
+ * select it, by disabling speculation (enabling mitigation).
+ */
+static inline void spec_mitigate(struct task_struct *task,
+				 unsigned long which)
+{
+	int state = arch_prctl_spec_ctrl_get(task, which);
+
+	if (state > 0 && (state & PR_SPEC_PRCTL))
+		arch_prctl_spec_ctrl_set(task, which, PR_SPEC_DISABLE);
+}
+
 static inline void seccomp_assign_mode(struct task_struct *task,
 				       unsigned long seccomp_mode)
 {
@@ -225,6 +240,8 @@ static inline void seccomp_assign_mode(struct task_struct *task,
 	 * filter) is set.
 	 */
 	smp_mb__before_atomic();
+	/* Assume seccomp processes want speculation flaw mitigation. */
+	spec_mitigate(task, PR_SPEC_STORE_BYPASS);
 	set_tsk_thread_flag(task, TIF_SECCOMP);
 }
 

[PATCH 4.4.y 075/101] prctl: Add force disable speculation

[Srivatsa S. Bhat]

From: Thomas Gleixner <tglx@linutronix.de>

commit 356e4bfff2c5489e016fdb925adbf12a1e3950ee upstream

For certain use cases it is desired to enforce mitigations so they cannot
be undone afterwards. That's important for loader stubs which want to
prevent a child from disabling the mitigation again. Will also be used for
seccomp(). The extra state preserving of the prctl state for SSB is a
preparatory step for EBPF dymanic speculation control.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 Documentation/spec_ctrl.txt |   34 +++++++++++++++++++++-------------
 arch/x86/kernel/cpu/bugs.c  |   35 +++++++++++++++++++++++++----------
 fs/proc/array.c             |    3 +++
 include/linux/sched.h       |    9 +++++++++
 include/uapi/linux/prctl.h  |    1 +
 5 files changed, 59 insertions(+), 23 deletions(-)

diff --git a/Documentation/spec_ctrl.txt b/Documentation/spec_ctrl.txt
index ddbebcd..1b3690d 100644
--- a/Documentation/spec_ctrl.txt
+++ b/Documentation/spec_ctrl.txt
@@ -25,19 +25,21 @@ PR_GET_SPECULATION_CTRL
 -----------------------
 
 PR_GET_SPECULATION_CTRL returns the state of the speculation misfeature
-which is selected with arg2 of prctl(2). The return value uses bits 0-2 with
+which is selected with arg2 of prctl(2). The return value uses bits 0-3 with
 the following meaning:
 
-==== ================ ===================================================
-Bit  Define           Description
-==== ================ ===================================================
-0    PR_SPEC_PRCTL    Mitigation can be controlled per task by
-                      PR_SET_SPECULATION_CTRL
-1    PR_SPEC_ENABLE   The speculation feature is enabled, mitigation is
-                      disabled
-2    PR_SPEC_DISABLE  The speculation feature is disabled, mitigation is
-                      enabled
-==== ================ ===================================================
+==== ===================== ===================================================
+Bit  Define                Description
+==== ===================== ===================================================
+0    PR_SPEC_PRCTL         Mitigation can be controlled per task by
+                           PR_SET_SPECULATION_CTRL
+1    PR_SPEC_ENABLE        The speculation feature is enabled, mitigation is
+                           disabled
+2    PR_SPEC_DISABLE       The speculation feature is disabled, mitigation is
+                           enabled
+3    PR_SPEC_FORCE_DISABLE Same as PR_SPEC_DISABLE, but cannot be undone. A
+                           subsequent prctl(..., PR_SPEC_ENABLE) will fail.
+==== ===================== ===================================================
 
 If all bits are 0 the CPU is not affected by the speculation misfeature.
 
@@ -47,9 +49,11 @@ misfeature will fail.
 
 PR_SET_SPECULATION_CTRL
 -----------------------
+
 PR_SET_SPECULATION_CTRL allows to control the speculation misfeature, which
 is selected by arg2 of :manpage:`prctl(2)` per task. arg3 is used to hand
-in the control value, i.e. either PR_SPEC_ENABLE or PR_SPEC_DISABLE.
+in the control value, i.e. either PR_SPEC_ENABLE or PR_SPEC_DISABLE or
+PR_SPEC_FORCE_DISABLE.
 
 Common error codes
 ------------------
@@ -70,10 +74,13 @@ Value   Meaning
 0       Success
 
 ERANGE  arg3 is incorrect, i.e. it's neither PR_SPEC_ENABLE nor
-        PR_SPEC_DISABLE
+        PR_SPEC_DISABLE nor PR_SPEC_FORCE_DISABLE
 
 ENXIO   Control of the selected speculation misfeature is not possible.
         See PR_GET_SPECULATION_CTRL.
+
+EPERM   Speculation was disabled with PR_SPEC_FORCE_DISABLE and caller
+        tried to enable it again.
 ======= =================================================================
 
 Speculation misfeature controls
@@ -84,3 +91,4 @@ Speculation misfeature controls
    * prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, 0, 0, 0);
    * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_ENABLE, 0, 0);
    * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE, 0, 0);
+   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_FORCE_DISABLE, 0, 0);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 64b54a4..d6897ca 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -531,21 +531,37 @@ static void ssb_select_mitigation()
 
 static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
 {
-	bool rds = !!test_tsk_thread_flag(task, TIF_RDS);
+	bool update;
 
 	if (ssb_mode != SPEC_STORE_BYPASS_PRCTL)
 		return -ENXIO;
 
-	if (ctrl == PR_SPEC_ENABLE)
-		clear_tsk_thread_flag(task, TIF_RDS);
-	else
-		set_tsk_thread_flag(task, TIF_RDS);
+	switch (ctrl) {
+	case PR_SPEC_ENABLE:
+		/* If speculation is force disabled, enable is not allowed */
+		if (task_spec_ssb_force_disable(task))
+			return -EPERM;
+		task_clear_spec_ssb_disable(task);
+		update = test_and_clear_tsk_thread_flag(task, TIF_RDS);
+		break;
+	case PR_SPEC_DISABLE:
+		task_set_spec_ssb_disable(task);
+		update = !test_and_set_tsk_thread_flag(task, TIF_RDS);
+		break;
+	case PR_SPEC_FORCE_DISABLE:
+		task_set_spec_ssb_disable(task);
+		task_set_spec_ssb_force_disable(task);
+		update = !test_and_set_tsk_thread_flag(task, TIF_RDS);
+		break;
+	default:
+		return -ERANGE;
+	}
 
 	/*
 	 * If being set on non-current task, delay setting the CPU
 	 * mitigation until it is next scheduled.
 	 */
-	if (task == current && rds != !!test_tsk_thread_flag(task, TIF_RDS))
+	if (task == current && update)
 		speculative_store_bypass_update();
 
 	return 0;
@@ -557,7 +573,9 @@ static int ssb_prctl_get(struct task_struct *task)
 	case SPEC_STORE_BYPASS_DISABLE:
 		return PR_SPEC_DISABLE;
 	case SPEC_STORE_BYPASS_PRCTL:
-		if (test_tsk_thread_flag(task, TIF_RDS))
+		if (task_spec_ssb_force_disable(task))
+			return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
+		if (task_spec_ssb_disable(task))
 			return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
 		return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
 	default:
@@ -570,9 +588,6 @@ static int ssb_prctl_get(struct task_struct *task)
 int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
 			     unsigned long ctrl)
 {
-	if (ctrl != PR_SPEC_ENABLE && ctrl != PR_SPEC_DISABLE)
-		return -ERANGE;
-
 	switch (which) {
 	case PR_SPEC_STORE_BYPASS:
 		return ssb_prctl_set(task, ctrl);
diff --git a/fs/proc/array.c b/fs/proc/array.c
index bb48358..3141478 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -341,6 +341,9 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p)
 	case PR_SPEC_NOT_AFFECTED:
 		seq_printf(m, "not vulnerable");
 		break;
+	case PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE:
+		seq_printf(m, "thread force mitigated");
+		break;
 	case PR_SPEC_PRCTL | PR_SPEC_DISABLE:
 		seq_printf(m, "thread mitigated");
 		break;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 90bea39..725498c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2167,6 +2167,8 @@ static inline void memalloc_noio_restore(unsigned int flags)
 #define PFA_NO_NEW_PRIVS 0	/* May not gain new privileges. */
 #define PFA_SPREAD_PAGE  1      /* Spread page cache over cpuset */
 #define PFA_SPREAD_SLAB  2      /* Spread some slab caches over cpuset */
+#define PFA_SPEC_SSB_DISABLE		4	/* Speculative Store Bypass disabled */
+#define PFA_SPEC_SSB_FORCE_DISABLE	5	/* Speculative Store Bypass force disabled*/
 
 
 #define TASK_PFA_TEST(name, func)					\
@@ -2190,6 +2192,13 @@ TASK_PFA_TEST(SPREAD_SLAB, spread_slab)
 TASK_PFA_SET(SPREAD_SLAB, spread_slab)
 TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab)
 
+TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable)
+TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable)
+TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable)
+
+TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)
+TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)
+
 /*
  * task->jobctl flags
  */
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 3b316be..64776b7 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -207,5 +207,6 @@ struct prctl_mm_map {
 # define PR_SPEC_PRCTL			(1UL << 0)
 # define PR_SPEC_ENABLE			(1UL << 1)
 # define PR_SPEC_DISABLE		(1UL << 2)
+# define PR_SPEC_FORCE_DISABLE		(1UL << 3)
 
 #endif /* _LINUX_PRCTL_H */

[PATCH 4.4.y 076/101] seccomp: Use PR_SPEC_FORCE_DISABLE

[Srivatsa S. Bhat]

From: Thomas Gleixner <tglx@linutronix.de>

commit b849a812f7eb92e96d1c8239b06581b2cfd8b275 upstream

Use PR_SPEC_FORCE_DISABLE in seccomp() because seccomp does not allow to
widen restrictions.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 kernel/seccomp.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index bfb1ee8..f33539f 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -226,7 +226,7 @@ static inline void spec_mitigate(struct task_struct *task,
 	int state = arch_prctl_spec_ctrl_get(task, which);
 
 	if (state > 0 && (state & PR_SPEC_PRCTL))
-		arch_prctl_spec_ctrl_set(task, which, PR_SPEC_DISABLE);
+		arch_prctl_spec_ctrl_set(task, which, PR_SPEC_FORCE_DISABLE);
 }
 
 static inline void seccomp_assign_mode(struct task_struct *task,

[PATCH 4.4.y 077/101] seccomp: Add filter flag to opt-out of SSB mitigation

[Srivatsa S. Bhat]

From: Kees Cook <keescook@chromium.org>

commit 00a02d0c502a06d15e07b857f8ff921e3e402675 upstream

If a seccomp user is not interested in Speculative Store Bypass mitigation
by default, it can set the new SECCOMP_FILTER_FLAG_SPEC_ALLOW flag when
adding filters.

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 include/linux/seccomp.h                       |    3 +
 include/uapi/linux/seccomp.h                  |    4 +
 kernel/seccomp.c                              |   19 ++++--
 tools/testing/selftests/seccomp/seccomp_bpf.c |   78 +++++++++++++++++++++++++
 4 files changed, 93 insertions(+), 11 deletions(-)

diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 2296e6b..5a53d34 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -3,7 +3,8 @@
 
 #include <uapi/linux/seccomp.h>
 
-#define SECCOMP_FILTER_FLAG_MASK	(SECCOMP_FILTER_FLAG_TSYNC)
+#define SECCOMP_FILTER_FLAG_MASK	(SECCOMP_FILTER_FLAG_TSYNC	| \
+					 SECCOMP_FILTER_FLAG_SPEC_ALLOW)
 
 #ifdef CONFIG_SECCOMP
 
diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
index 0f238a4..e4acb61 100644
--- a/include/uapi/linux/seccomp.h
+++ b/include/uapi/linux/seccomp.h
@@ -15,7 +15,9 @@
 #define SECCOMP_SET_MODE_FILTER	1
 
 /* Valid flags for SECCOMP_SET_MODE_FILTER */
-#define SECCOMP_FILTER_FLAG_TSYNC	1
+#define SECCOMP_FILTER_FLAG_TSYNC	(1UL << 0)
+/* In v4.14+ SECCOMP_FILTER_FLAG_LOG is (1UL << 1) */
+#define SECCOMP_FILTER_FLAG_SPEC_ALLOW	(1UL << 2)
 
 /*
  * All BPF programs must return a 32-bit value.
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index f33539f..4bb8a5a 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -230,7 +230,8 @@ static inline void spec_mitigate(struct task_struct *task,
 }
 
 static inline void seccomp_assign_mode(struct task_struct *task,
-				       unsigned long seccomp_mode)
+				       unsigned long seccomp_mode,
+				       unsigned long flags)
 {
 	assert_spin_locked(&task->sighand->siglock);
 
@@ -240,8 +241,9 @@ static inline void seccomp_assign_mode(struct task_struct *task,
 	 * filter) is set.
 	 */
 	smp_mb__before_atomic();
-	/* Assume seccomp processes want speculation flaw mitigation. */
-	spec_mitigate(task, PR_SPEC_STORE_BYPASS);
+	/* Assume default seccomp processes want spec flaw mitigation. */
+	if ((flags & SECCOMP_FILTER_FLAG_SPEC_ALLOW) == 0)
+		spec_mitigate(task, PR_SPEC_STORE_BYPASS);
 	set_tsk_thread_flag(task, TIF_SECCOMP);
 }
 
@@ -309,7 +311,7 @@ static inline pid_t seccomp_can_sync_threads(void)
  * without dropping the locks.
  *
  */
-static inline void seccomp_sync_threads(void)
+static inline void seccomp_sync_threads(unsigned long flags)
 {
 	struct task_struct *thread, *caller;
 
@@ -350,7 +352,8 @@ static inline void seccomp_sync_threads(void)
 		 * allow one thread to transition the other.
 		 */
 		if (thread->seccomp.mode == SECCOMP_MODE_DISABLED)
-			seccomp_assign_mode(thread, SECCOMP_MODE_FILTER);
+			seccomp_assign_mode(thread, SECCOMP_MODE_FILTER,
+					    flags);
 	}
 }
 
@@ -469,7 +472,7 @@ static long seccomp_attach_filter(unsigned int flags,
 
 	/* Now that the new filter is in place, synchronize to all threads. */
 	if (flags & SECCOMP_FILTER_FLAG_TSYNC)
-		seccomp_sync_threads();
+		seccomp_sync_threads(flags);
 
 	return 0;
 }
@@ -764,7 +767,7 @@ static long seccomp_set_mode_strict(void)
 #ifdef TIF_NOTSC
 	disable_TSC();
 #endif
-	seccomp_assign_mode(current, seccomp_mode);
+	seccomp_assign_mode(current, seccomp_mode, 0);
 	ret = 0;
 
 out:
@@ -822,7 +825,7 @@ static long seccomp_set_mode_filter(unsigned int flags,
 	/* Do not free the successfully attached filter. */
 	prepared = NULL;
 
-	seccomp_assign_mode(current, seccomp_mode);
+	seccomp_assign_mode(current, seccomp_mode, flags);
 out:
 	spin_unlock_irq(&current->sighand->siglock);
 	if (flags & SECCOMP_FILTER_FLAG_TSYNC)
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 29487e0..b3f3454 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -1477,7 +1477,11 @@ TEST_F(TRACE_syscall, syscall_dropped)
 #endif
 
 #ifndef SECCOMP_FILTER_FLAG_TSYNC
-#define SECCOMP_FILTER_FLAG_TSYNC 1
+#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0)
+#endif
+
+#ifndef SECCOMP_FILTER_FLAG_SPEC_ALLOW
+#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2)
 #endif
 
 #ifndef seccomp
@@ -1576,6 +1580,78 @@ TEST(seccomp_syscall_mode_lock)
 	}
 }
 
+/*
+ * Test detection of known and unknown filter flags. Userspace needs to be able
+ * to check if a filter flag is supported by the current kernel and a good way
+ * of doing that is by attempting to enter filter mode, with the flag bit in
+ * question set, and a NULL pointer for the _args_ parameter. EFAULT indicates
+ * that the flag is valid and EINVAL indicates that the flag is invalid.
+ */
+TEST(detect_seccomp_filter_flags)
+{
+	unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC,
+				 SECCOMP_FILTER_FLAG_SPEC_ALLOW };
+	unsigned int flag, all_flags;
+	int i;
+	long ret;
+
+	/* Test detection of known-good filter flags */
+	for (i = 0, all_flags = 0; i < ARRAY_SIZE(flags); i++) {
+		int bits = 0;
+
+		flag = flags[i];
+		/* Make sure the flag is a single bit! */
+		while (flag) {
+			if (flag & 0x1)
+				bits ++;
+			flag >>= 1;
+		}
+		ASSERT_EQ(1, bits);
+		flag = flags[i];
+
+		ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
+		ASSERT_NE(ENOSYS, errno) {
+			TH_LOG("Kernel does not support seccomp syscall!");
+		}
+		EXPECT_EQ(-1, ret);
+		EXPECT_EQ(EFAULT, errno) {
+			TH_LOG("Failed to detect that a known-good filter flag (0x%X) is supported!",
+			       flag);
+		}
+
+		all_flags |= flag;
+	}
+
+	/* Test detection of all known-good filter flags */
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, all_flags, NULL);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EFAULT, errno) {
+		TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!",
+		       all_flags);
+	}
+
+	/* Test detection of an unknown filter flag */
+	flag = -1;
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno) {
+		TH_LOG("Failed to detect that an unknown filter flag (0x%X) is unsupported!",
+		       flag);
+	}
+
+	/*
+	 * Test detection of an unknown filter flag that may simply need to be
+	 * added to this test
+	 */
+	flag = flags[ARRAY_SIZE(flags) - 1] << 1;
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno) {
+		TH_LOG("Failed to detect that an unknown filter flag (0x%X) is unsupported! Does a new flag need to be added to this test?",
+		       flag);
+	}
+}
+
 TEST(TSYNC_first)
 {
 	struct sock_filter filter[] = {

[PATCH 4.4.y 078/101] seccomp: Move speculation migitation control to arch code

[Srivatsa S. Bhat]

From: Thomas Gleixner <tglx@linutronix.de>

commit 8bf37d8c067bb7eb8e7c381bdadf9bd89182b6bc upstream

The migitation control is simpler to implement in architecture code as it
avoids the extra function call to check the mode. Aside of that having an
explicit seccomp enabled mode in the architecture mitigations would require
even more workarounds.

Move it into architecture code and provide a weak function in the seccomp
code. Remove the 'which' argument as this allows the architecture to decide
which mitigations are relevant for seccomp.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/bugs.c |   29 ++++++++++++++++++-----------
 include/linux/nospec.h     |    2 ++
 kernel/seccomp.c           |   15 ++-------------
 3 files changed, 22 insertions(+), 24 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index d6897ca..b005ef7 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -567,6 +567,24 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
 	return 0;
 }
 
+int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
+			     unsigned long ctrl)
+{
+	switch (which) {
+	case PR_SPEC_STORE_BYPASS:
+		return ssb_prctl_set(task, ctrl);
+	default:
+		return -ENODEV;
+	}
+}
+
+#ifdef CONFIG_SECCOMP
+void arch_seccomp_spec_mitigate(struct task_struct *task)
+{
+	ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE);
+}
+#endif
+
 static int ssb_prctl_get(struct task_struct *task)
 {
 	switch (ssb_mode) {
@@ -585,17 +603,6 @@ static int ssb_prctl_get(struct task_struct *task)
 	}
 }
 
-int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
-			     unsigned long ctrl)
-{
-	switch (which) {
-	case PR_SPEC_STORE_BYPASS:
-		return ssb_prctl_set(task, ctrl);
-	default:
-		return -ENODEV;
-	}
-}
-
 int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
 {
 	switch (which) {
diff --git a/include/linux/nospec.h b/include/linux/nospec.h
index a908c95..0c5ef54 100644
--- a/include/linux/nospec.h
+++ b/include/linux/nospec.h
@@ -62,5 +62,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
 int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which);
 int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
 			     unsigned long ctrl);
+/* Speculation control for seccomp enforced mitigation */
+void arch_seccomp_spec_mitigate(struct task_struct *task);
 
 #endif /* _LINUX_NOSPEC_H */
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 4bb8a5a..9a9203b 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -216,18 +216,7 @@ static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode)
 	return true;
 }
 
-/*
- * If a given speculation mitigation is opt-in (prctl()-controlled),
- * select it, by disabling speculation (enabling mitigation).
- */
-static inline void spec_mitigate(struct task_struct *task,
-				 unsigned long which)
-{
-	int state = arch_prctl_spec_ctrl_get(task, which);
-
-	if (state > 0 && (state & PR_SPEC_PRCTL))
-		arch_prctl_spec_ctrl_set(task, which, PR_SPEC_FORCE_DISABLE);
-}
+void __weak arch_seccomp_spec_mitigate(struct task_struct *task) { }
 
 static inline void seccomp_assign_mode(struct task_struct *task,
 				       unsigned long seccomp_mode,
@@ -243,7 +232,7 @@ static inline void seccomp_assign_mode(struct task_struct *task,
 	smp_mb__before_atomic();
 	/* Assume default seccomp processes want spec flaw mitigation. */
 	if ((flags & SECCOMP_FILTER_FLAG_SPEC_ALLOW) == 0)
-		spec_mitigate(task, PR_SPEC_STORE_BYPASS);
+		arch_seccomp_spec_mitigate(task);
 	set_tsk_thread_flag(task, TIF_SECCOMP);
 }
 

[PATCH 4.4.y 079/101] x86/speculation: Make "seccomp" the default mode for Speculative Store Bypass

[Srivatsa S. Bhat]

From: Kees Cook <keescook@chromium.org>

commit f21b53b20c754021935ea43364dbf53778eeba32 upstream

Unless explicitly opted out of, anything running under seccomp will have
SSB mitigations enabled. Choosing the "prctl" mode will disable this.

[ tglx: Adjusted it to the new arch_seccomp_spec_mitigate() mechanism ]

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 Documentation/kernel-parameters.txt  |   26 +++++++++++++++++---------
 arch/x86/include/asm/nospec-branch.h |    1 +
 arch/x86/kernel/cpu/bugs.c           |   32 +++++++++++++++++++++++---------
 3 files changed, 41 insertions(+), 18 deletions(-)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 80202de..3fd53e1 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3647,19 +3647,27 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			This parameter controls whether the Speculative Store
 			Bypass optimization is used.
 
-			on     - Unconditionally disable Speculative Store Bypass
-			off    - Unconditionally enable Speculative Store Bypass
-			auto   - Kernel detects whether the CPU model contains an
-				 implementation of Speculative Store Bypass and
-				 picks the most appropriate mitigation.
-			prctl  - Control Speculative Store Bypass per thread
-				 via prctl. Speculative Store Bypass is enabled
-				 for a process by default. The state of the control
-				 is inherited on fork.
+			on      - Unconditionally disable Speculative Store Bypass
+			off     - Unconditionally enable Speculative Store Bypass
+			auto    - Kernel detects whether the CPU model contains an
+				  implementation of Speculative Store Bypass and
+				  picks the most appropriate mitigation. If the
+				  CPU is not vulnerable, "off" is selected. If the
+				  CPU is vulnerable the default mitigation is
+				  architecture and Kconfig dependent. See below.
+			prctl   - Control Speculative Store Bypass per thread
+				  via prctl. Speculative Store Bypass is enabled
+				  for a process by default. The state of the control
+				  is inherited on fork.
+			seccomp - Same as "prctl" above, but all seccomp threads
+				  will disable SSB unless they explicitly opt out.
 
 			Not specifying this option is equivalent to
 			spec_store_bypass_disable=auto.
 
+			Default mitigations:
+			X86:	If CONFIG_SECCOMP=y "seccomp", otherwise "prctl"
+
 	spia_io_base=	[HW,MTD]
 	spia_fio_base=
 	spia_pedr=
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 155d955..930c1594 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -188,6 +188,7 @@ enum ssb_mitigation {
 	SPEC_STORE_BYPASS_NONE,
 	SPEC_STORE_BYPASS_DISABLE,
 	SPEC_STORE_BYPASS_PRCTL,
+	SPEC_STORE_BYPASS_SECCOMP,
 };
 
 extern char __indirect_thunk_start[];
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index b005ef7..6fd3fcf 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -414,22 +414,25 @@ enum ssb_mitigation_cmd {
 	SPEC_STORE_BYPASS_CMD_AUTO,
 	SPEC_STORE_BYPASS_CMD_ON,
 	SPEC_STORE_BYPASS_CMD_PRCTL,
+	SPEC_STORE_BYPASS_CMD_SECCOMP,
 };
 
 static const char *ssb_strings[] = {
 	[SPEC_STORE_BYPASS_NONE]	= "Vulnerable",
 	[SPEC_STORE_BYPASS_DISABLE]	= "Mitigation: Speculative Store Bypass disabled",
-	[SPEC_STORE_BYPASS_PRCTL]	= "Mitigation: Speculative Store Bypass disabled via prctl"
+	[SPEC_STORE_BYPASS_PRCTL]	= "Mitigation: Speculative Store Bypass disabled via prctl",
+	[SPEC_STORE_BYPASS_SECCOMP]	= "Mitigation: Speculative Store Bypass disabled via prctl and seccomp",
 };
 
 static const struct {
 	const char *option;
 	enum ssb_mitigation_cmd cmd;
 } ssb_mitigation_options[] = {
-	{ "auto",	SPEC_STORE_BYPASS_CMD_AUTO },  /* Platform decides */
-	{ "on",		SPEC_STORE_BYPASS_CMD_ON },    /* Disable Speculative Store Bypass */
-	{ "off",	SPEC_STORE_BYPASS_CMD_NONE },  /* Don't touch Speculative Store Bypass */
-	{ "prctl",	SPEC_STORE_BYPASS_CMD_PRCTL }, /* Disable Speculative Store Bypass via prctl */
+	{ "auto",	SPEC_STORE_BYPASS_CMD_AUTO },    /* Platform decides */
+	{ "on",		SPEC_STORE_BYPASS_CMD_ON },      /* Disable Speculative Store Bypass */
+	{ "off",	SPEC_STORE_BYPASS_CMD_NONE },    /* Don't touch Speculative Store Bypass */
+	{ "prctl",	SPEC_STORE_BYPASS_CMD_PRCTL },   /* Disable Speculative Store Bypass via prctl */
+	{ "seccomp",	SPEC_STORE_BYPASS_CMD_SECCOMP }, /* Disable Speculative Store Bypass via prctl and seccomp */
 };
 
 static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void)
@@ -479,8 +482,15 @@ static enum ssb_mitigation_cmd __init __ssb_select_mitigation(void)
 
 	switch (cmd) {
 	case SPEC_STORE_BYPASS_CMD_AUTO:
-		/* Choose prctl as the default mode */
-		mode = SPEC_STORE_BYPASS_PRCTL;
+	case SPEC_STORE_BYPASS_CMD_SECCOMP:
+		/*
+		 * Choose prctl+seccomp as the default mode if seccomp is
+		 * enabled.
+		 */
+		if (IS_ENABLED(CONFIG_SECCOMP))
+			mode = SPEC_STORE_BYPASS_SECCOMP;
+		else
+			mode = SPEC_STORE_BYPASS_PRCTL;
 		break;
 	case SPEC_STORE_BYPASS_CMD_ON:
 		mode = SPEC_STORE_BYPASS_DISABLE;
@@ -528,12 +538,14 @@ static void ssb_select_mitigation()
 }
 
 #undef pr_fmt
+#define pr_fmt(fmt)     "Speculation prctl: " fmt
 
 static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
 {
 	bool update;
 
-	if (ssb_mode != SPEC_STORE_BYPASS_PRCTL)
+	if (ssb_mode != SPEC_STORE_BYPASS_PRCTL &&
+	    ssb_mode != SPEC_STORE_BYPASS_SECCOMP)
 		return -ENXIO;
 
 	switch (ctrl) {
@@ -581,7 +593,8 @@ int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
 #ifdef CONFIG_SECCOMP
 void arch_seccomp_spec_mitigate(struct task_struct *task)
 {
-	ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE);
+	if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP)
+		ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE);
 }
 #endif
 
@@ -590,6 +603,7 @@ static int ssb_prctl_get(struct task_struct *task)
 	switch (ssb_mode) {
 	case SPEC_STORE_BYPASS_DISABLE:
 		return PR_SPEC_DISABLE;
+	case SPEC_STORE_BYPASS_SECCOMP:
 	case SPEC_STORE_BYPASS_PRCTL:
 		if (task_spec_ssb_force_disable(task))
 			return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;

[PATCH 4.4.y 081/101] proc: Use underscores for SSBD in 'status'

[Srivatsa S. Bhat]

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

commit e96f46ee8587607a828f783daa6eb5b44d25004d upstream

The style for the 'status' file is CamelCase or this. _.

Fixes: fae1fa0fc ("proc: Provide details on speculation flaw mitigations")
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 fs/proc/array.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/proc/array.c b/fs/proc/array.c
index 3141478..cb71cba 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -333,7 +333,7 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p)
 #ifdef CONFIG_SECCOMP
 	seq_printf(m, "Seccomp:\t%d\n", p->seccomp.mode);
 #endif
-	seq_printf(m, "\nSpeculation Store Bypass:\t");
+	seq_printf(m, "\nSpeculation_Store_Bypass:\t");
 	switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) {
 	case -EINVAL:
 		seq_printf(m, "unknown");

[PATCH 4.4.y 082/101] Documentation/spec_ctrl: Do some minor cleanups

[Srivatsa S. Bhat]

From: Borislav Petkov <bp@suse.de>

commit dd0792699c4058e63c0715d9a7c2d40226fcdddc upstream

Fix some typos, improve formulations, end sentences with a fullstop.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 Documentation/spec_ctrl.txt |   24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/Documentation/spec_ctrl.txt b/Documentation/spec_ctrl.txt
index 1b3690d..32f3d55 100644
--- a/Documentation/spec_ctrl.txt
+++ b/Documentation/spec_ctrl.txt
@@ -2,13 +2,13 @@
 Speculation Control
 ===================
 
-Quite some CPUs have speculation related misfeatures which are in fact
-vulnerabilites causing data leaks in various forms even accross privilege
-domains.
+Quite some CPUs have speculation-related misfeatures which are in
+fact vulnerabilities causing data leaks in various forms even across
+privilege domains.
 
 The kernel provides mitigation for such vulnerabilities in various
-forms. Some of these mitigations are compile time configurable and some on
-the kernel command line.
+forms. Some of these mitigations are compile-time configurable and some
+can be supplied on the kernel command line.
 
 There is also a class of mitigations which are very expensive, but they can
 be restricted to a certain set of processes or tasks in controlled
@@ -32,18 +32,18 @@ the following meaning:
 Bit  Define                Description
 ==== ===================== ===================================================
 0    PR_SPEC_PRCTL         Mitigation can be controlled per task by
-                           PR_SET_SPECULATION_CTRL
+                           PR_SET_SPECULATION_CTRL.
 1    PR_SPEC_ENABLE        The speculation feature is enabled, mitigation is
-                           disabled
+                           disabled.
 2    PR_SPEC_DISABLE       The speculation feature is disabled, mitigation is
-                           enabled
+                           enabled.
 3    PR_SPEC_FORCE_DISABLE Same as PR_SPEC_DISABLE, but cannot be undone. A
                            subsequent prctl(..., PR_SPEC_ENABLE) will fail.
 ==== ===================== ===================================================
 
 If all bits are 0 the CPU is not affected by the speculation misfeature.
 
-If PR_SPEC_PRCTL is set, then the per task control of the mitigation is
+If PR_SPEC_PRCTL is set, then the per-task control of the mitigation is
 available. If not set, prctl(PR_SET_SPECULATION_CTRL) for the speculation
 misfeature will fail.
 
@@ -61,9 +61,9 @@ Common error codes
 Value   Meaning
 ======= =================================================================
 EINVAL  The prctl is not implemented by the architecture or unused
-        prctl(2) arguments are not 0
+        prctl(2) arguments are not 0.
 
-ENODEV  arg2 is selecting a not supported speculation misfeature
+ENODEV  arg2 is selecting a not supported speculation misfeature.
 ======= =================================================================
 
 PR_SET_SPECULATION_CTRL error codes
@@ -74,7 +74,7 @@ Value   Meaning
 0       Success
 
 ERANGE  arg3 is incorrect, i.e. it's neither PR_SPEC_ENABLE nor
-        PR_SPEC_DISABLE nor PR_SPEC_FORCE_DISABLE
+        PR_SPEC_DISABLE nor PR_SPEC_FORCE_DISABLE.
 
 ENXIO   Control of the selected speculation misfeature is not possible.
         See PR_GET_SPECULATION_CTRL.

[PATCH 4.4.y 083/101] x86/bugs: Fix __ssb_select_mitigation() return type

[Srivatsa S. Bhat]

From: Jiri Kosina <jkosina@suse.cz>

commit d66d8ff3d21667b41eddbe86b35ab411e40d8c5f upstream

__ssb_select_mitigation() returns one of the members of enum ssb_mitigation,
not ssb_mitigation_cmd; fix the prototype to reflect that.

Fixes: 24f7fc83b9204 ("x86/bugs: Provide boot parameters for the spec_store_bypass_disable mitigation")
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/bugs.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 812e92a..5b58b76 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -466,7 +466,7 @@ static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void)
 	return cmd;
 }
 
-static enum ssb_mitigation_cmd __init __ssb_select_mitigation(void)
+static enum ssb_mitigation __init __ssb_select_mitigation(void)
 {
 	enum ssb_mitigation mode = SPEC_STORE_BYPASS_NONE;
 	enum ssb_mitigation_cmd cmd;

[PATCH 4.4.y 084/101] x86/bugs: Make cpu_show_common() static

[Srivatsa S. Bhat]

From: Jiri Kosina <jkosina@suse.cz>

commit 7bb4d366cba992904bffa4820d24e70a3de93e76 upstream

cpu_show_common() is not used outside of arch/x86/kernel/cpu/bugs.c, so
make it static.

Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/bugs.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 5b58b76..512be68 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -638,7 +638,7 @@ void x86_spec_ctrl_setup_ap(void)
 
 #ifdef CONFIG_SYSFS
 
-ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
+static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			char *buf, unsigned int bug)
 {
 	if (!boot_cpu_has_bug(bug))

[PATCH 4.4.y 085/101] x86/bugs: Fix the parameters alignment and missing void

[Srivatsa S. Bhat]

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

commit ffed645e3be0e32f8e9ab068d257aee8d0fe8eec upstream

Fixes: 7bb4d366c ("x86/bugs: Make cpu_show_common() static")
Fixes: 24f7fc83b ("x86/bugs: Provide boot parameters for the spec_store_bypass_disable mitigation")
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/bugs.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 512be68..84de0fc 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -529,7 +529,7 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
 	return mode;
 }
 
-static void ssb_select_mitigation()
+static void ssb_select_mitigation(void)
 {
 	ssb_mode = __ssb_select_mitigation();
 
@@ -639,7 +639,7 @@ void x86_spec_ctrl_setup_ap(void)
 #ifdef CONFIG_SYSFS
 
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
-			char *buf, unsigned int bug)
+			       char *buf, unsigned int bug)
 {
 	if (!boot_cpu_has_bug(bug))
 		return sprintf(buf, "Not affected\n");

[PATCH 4.4.y 086/101] x86/cpu: Make alternative_msr_write work for 32-bit code

[Srivatsa S. Bhat]

From: Jim Mattson <jmattson@google.com>

commit 5f2b745f5e1304f438f9b2cd03ebc8120b6e0d3b upstream

Cast val and (val >> 32) to (u32), so that they fit in a
general-purpose register in both 32-bit and 64-bit code.

[ tglx: Made it u32 instead of uintptr_t ]

Fixes: c65732e4f721 ("x86/cpu: Restore CPUID_8000_0008_EBX reload")
Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/nospec-branch.h |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 930c1594..640c11b 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -219,8 +219,8 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
 {
 	asm volatile(ALTERNATIVE("", "wrmsr", %c[feature])
 		: : "c" (msr),
-		    "a" (val),
-		    "d" (val >> 32),
+		    "a" ((u32)val),
+		    "d" ((u32)(val >> 32)),
 		    [feature] "i" (feature)
 		: "memory");
 }

[PATCH 4.4.y 087/101] x86/speculation: Use synthetic bits for IBRS/IBPB/STIBP

[Srivatsa S. Bhat]

From: Borislav Petkov <bp@suse.de>

commit e7c587da125291db39ddf1f49b18e5970adbac17 upstream

Intel and AMD have different CPUID bits hence for those use synthetic bits
which get set on the respective vendor's in init_speculation_control(). So
that debacles like what the commit message of

  c65732e4f721 ("x86/cpu: Restore CPUID_8000_0008_EBX reload")

talks about don't happen anymore.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Jörg Otte <jrg.otte@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Link: https://lkml.kernel.org/r/20180504161815.GG9257@pd.tnic
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Srivatsa: Backported to 4.4.y, skipping the KVM changes in this patch. ]
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeatures.h |   12 ++++++++----
 arch/x86/kernel/cpu/common.c       |   14 ++++++++++----
 2 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 97926be..9f64d10 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -204,7 +204,10 @@
 #define X86_FEATURE_USE_IBPB	( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled*/
 #define X86_FEATURE_USE_IBRS_FW	( 7*32+22) /* "" Use IBRS during runtime firmware calls */
 #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE	( 7*32+23) /* "" Disable Speculative Store Bypass. */
-#define X86_FEATURE_AMD_SSBD	(7*32+24)  /* "" AMD SSBD implementation */
+#define X86_FEATURE_AMD_SSBD	( 7*32+24) /* "" AMD SSBD implementation */
+#define X86_FEATURE_IBRS	( 7*32+25) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_IBPB	( 7*32+26) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_STIBP	( 7*32+27) /* Single Thread Indirect Branch Predictors */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
@@ -256,9 +259,9 @@
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
 #define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
-#define X86_FEATURE_IBPB	(13*32+12) /* Indirect Branch Prediction Barrier */
-#define X86_FEATURE_IBRS	(13*32+14) /* Indirect Branch Restricted Speculation */
-#define X86_FEATURE_STIBP	(13*32+15) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_IBPB	(13*32+12) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_AMD_IBRS	(13*32+14) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_AMD_STIBP	(13*32+15) /* Single Thread Indirect Branch Predictors */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
 #define X86_FEATURE_DTHERM	(14*32+ 0) /* Digital Thermal Sensor */
@@ -293,6 +296,7 @@
 #define X86_FEATURE_SUCCOR	(17*32+1) /* Uncorrectable error containment and recovery */
 #define X86_FEATURE_SMCA	(17*32+3) /* Scalable MCA */
 
+
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 6f3a5d7..f2b579f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -683,17 +683,23 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
 	 * and they also have a different bit for STIBP support. Also,
 	 * a hypervisor might have set the individual AMD bits even on
 	 * Intel CPUs, for finer-grained selection of what's available.
-	 *
-	 * We use the AMD bits in 0x8000_0008 EBX as the generic hardware
-	 * features, which are visible in /proc/cpuinfo and used by the
-	 * kernel. So set those accordingly from the Intel bits.
 	 */
 	if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) {
 		set_cpu_cap(c, X86_FEATURE_IBRS);
 		set_cpu_cap(c, X86_FEATURE_IBPB);
 	}
+
 	if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
 		set_cpu_cap(c, X86_FEATURE_STIBP);
+
+	if (cpu_has(c, X86_FEATURE_AMD_IBRS))
+		set_cpu_cap(c, X86_FEATURE_IBRS);
+
+	if (cpu_has(c, X86_FEATURE_AMD_IBPB))
+		set_cpu_cap(c, X86_FEATURE_IBPB);
+
+	if (cpu_has(c, X86_FEATURE_AMD_STIBP))
+		set_cpu_cap(c, X86_FEATURE_STIBP);
 }
 
 void get_cpu_cap(struct cpuinfo_x86 *c)

[PATCH 4.4.y 088/101] x86/cpufeatures: Disentangle MSR_SPEC_CTRL enumeration from IBRS

[Srivatsa S. Bhat]

From: Thomas Gleixner <tglx@linutronix.de>

commit 7eb8956a7fec3c1f0abc2a5517dada99ccc8a961 upstream

The availability of the SPEC_CTRL MSR is enumerated by a CPUID bit on
Intel and implied by IBRS or STIBP support on AMD. That's just confusing
and in case an AMD CPU has IBRS not supported because the underlying
problem has been fixed but has another bit valid in the SPEC_CTRL MSR,
the thing falls apart.

Add a synthetic feature bit X86_FEATURE_MSR_SPEC_CTRL to denote the
availability on both Intel and AMD.

While at it replace the boot_cpu_has() checks with static_cpu_has() where
possible. This prevents late microcode loading from exposing SPEC_CTRL, but
late loading is already very limited as it does not reevaluate the
mitigation options and other bits and pieces. Having static_cpu_has() is
the simplest and least fragile solution.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeatures.h |    3 +++
 arch/x86/kernel/cpu/bugs.c         |   18 +++++++++++-------
 arch/x86/kernel/cpu/common.c       |    9 +++++++--
 arch/x86/kernel/cpu/intel.c        |    1 +
 4 files changed, 22 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 9f64d10..dd04cd7 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -198,6 +198,9 @@
 
 #define X86_FEATURE_RETPOLINE	( 7*32+29) /* "" Generic Retpoline mitigation for Spectre variant 2 */
 #define X86_FEATURE_RETPOLINE_AMD ( 7*32+30) /* "" AMD Retpoline mitigation for Spectre variant 2 */
+
+#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
+
 /* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */
 #define X86_FEATURE_KAISER	( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */
 
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 84de0fc..e23e289 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -63,7 +63,7 @@ void __init check_bugs(void)
 	 * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD
 	 * init code as it is not enumerated and depends on the family.
 	 */
-	if (boot_cpu_has(X86_FEATURE_IBRS))
+	if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
 		rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
 
 	/* Select the proper spectre mitigation before patching alternatives */
@@ -143,7 +143,7 @@ u64 x86_spec_ctrl_get_default(void)
 {
 	u64 msrval = x86_spec_ctrl_base;
 
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+	if (static_cpu_has(X86_FEATURE_SPEC_CTRL))
 		msrval |= ssbd_tif_to_spec_ctrl(current_thread_info()->flags);
 	return msrval;
 }
@@ -153,10 +153,12 @@ void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl)
 {
 	u64 host = x86_spec_ctrl_base;
 
-	if (!boot_cpu_has(X86_FEATURE_IBRS))
+	/* Is MSR_SPEC_CTRL implemented ? */
+	if (!static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
 		return;
 
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+	/* Intel controls SSB in MSR_SPEC_CTRL */
+	if (static_cpu_has(X86_FEATURE_SPEC_CTRL))
 		host |= ssbd_tif_to_spec_ctrl(current_thread_info()->flags);
 
 	if (host != guest_spec_ctrl)
@@ -168,10 +170,12 @@ void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl)
 {
 	u64 host = x86_spec_ctrl_base;
 
-	if (!boot_cpu_has(X86_FEATURE_IBRS))
+	/* Is MSR_SPEC_CTRL implemented ? */
+	if (!static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
 		return;
 
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+	/* Intel controls SSB in MSR_SPEC_CTRL */
+	if (static_cpu_has(X86_FEATURE_SPEC_CTRL))
 		host |= ssbd_tif_to_spec_ctrl(current_thread_info()->flags);
 
 	if (host != guest_spec_ctrl)
@@ -629,7 +633,7 @@ int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
 
 void x86_spec_ctrl_setup_ap(void)
 {
-	if (boot_cpu_has(X86_FEATURE_IBRS))
+	if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
 		x86_spec_ctrl_set(x86_spec_ctrl_base & ~x86_spec_ctrl_mask);
 
 	if (ssb_mode == SPEC_STORE_BYPASS_DISABLE)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f2b579f..1f70ff1 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -687,19 +687,24 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) {
 		set_cpu_cap(c, X86_FEATURE_IBRS);
 		set_cpu_cap(c, X86_FEATURE_IBPB);
+		set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
 	}
 
 	if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
 		set_cpu_cap(c, X86_FEATURE_STIBP);
 
-	if (cpu_has(c, X86_FEATURE_AMD_IBRS))
+	if (cpu_has(c, X86_FEATURE_AMD_IBRS)) {
 		set_cpu_cap(c, X86_FEATURE_IBRS);
+		set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
+	}
 
 	if (cpu_has(c, X86_FEATURE_AMD_IBPB))
 		set_cpu_cap(c, X86_FEATURE_IBPB);
 
-	if (cpu_has(c, X86_FEATURE_AMD_STIBP))
+	if (cpu_has(c, X86_FEATURE_AMD_STIBP)) {
 		set_cpu_cap(c, X86_FEATURE_STIBP);
+		set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
+	}
 }
 
 void get_cpu_cap(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index a34e357..9a84e75 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -118,6 +118,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		setup_clear_cpu_cap(X86_FEATURE_IBPB);
 		setup_clear_cpu_cap(X86_FEATURE_STIBP);
 		setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL);
+		setup_clear_cpu_cap(X86_FEATURE_MSR_SPEC_CTRL);
 		setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP);
 		setup_clear_cpu_cap(X86_FEATURE_SSBD);
 	}

[PATCH 4.4.y 089/101] x86/cpufeatures: Disentangle SSBD enumeration

[Srivatsa S. Bhat]

From: Thomas Gleixner <tglx@linutronix.de>

commit 52817587e706686fcdb27f14c1b000c92f266c96 upstream

The SSBD enumeration is similarly to the other bits magically shared
between Intel and AMD though the mechanisms are different.

Make X86_FEATURE_SSBD synthetic and set it depending on the vendor specific
features or family dependent setup.

Change the Intel bit to X86_FEATURE_SPEC_CTRL_SSBD to denote that SSBD is
controlled via MSR_SPEC_CTRL and fix up the usage sites.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeatures.h |    6 ++++--
 arch/x86/kernel/cpu/amd.c          |    7 +------
 arch/x86/kernel/cpu/bugs.c         |   10 +++++-----
 arch/x86/kernel/cpu/common.c       |    3 +++
 arch/x86/kernel/cpu/intel.c        |    1 +
 arch/x86/kernel/process.c          |    2 +-
 6 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index dd04cd7..7dd1bba 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -200,6 +200,7 @@
 #define X86_FEATURE_RETPOLINE_AMD ( 7*32+30) /* "" AMD Retpoline mitigation for Spectre variant 2 */
 
 #define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
+#define X86_FEATURE_SSBD	( 7*32+17) /* Speculative Store Bypass Disable */
 
 /* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */
 #define X86_FEATURE_KAISER	( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */
@@ -207,7 +208,8 @@
 #define X86_FEATURE_USE_IBPB	( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled*/
 #define X86_FEATURE_USE_IBRS_FW	( 7*32+22) /* "" Use IBRS during runtime firmware calls */
 #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE	( 7*32+23) /* "" Disable Speculative Store Bypass. */
-#define X86_FEATURE_AMD_SSBD	( 7*32+24) /* "" AMD SSBD implementation */
+#define X86_FEATURE_LS_CFG_SSBD	( 7*32+24) /* "" AMD SSBD implementation */
+
 #define X86_FEATURE_IBRS	( 7*32+25) /* Indirect Branch Restricted Speculation */
 #define X86_FEATURE_IBPB	( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP	( 7*32+27) /* Single Thread Indirect Branch Predictors */
@@ -306,7 +308,7 @@
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
-#define X86_FEATURE_SSBD		(18*32+31) /* Speculative Store Bypass Disable */
+#define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 
 /*
  * BUG word(s)
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index bd0edb2..a97fd67 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -535,8 +535,8 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		 * avoid RMW. If that faults, do not enable SSBD.
 		 */
 		if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
+			setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD);
 			setup_force_cpu_cap(X86_FEATURE_SSBD);
-			setup_force_cpu_cap(X86_FEATURE_AMD_SSBD);
 			x86_amd_ls_cfg_ssbd_mask = 1ULL << bit;
 		}
 	}
@@ -815,11 +815,6 @@ static void init_amd(struct cpuinfo_x86 *c)
 	/* AMD CPUs don't reset SS attributes on SYSRET, Xen does. */
 	if (!cpu_has(c, X86_FEATURE_XENPV))
 		set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
-
-	if (boot_cpu_has(X86_FEATURE_AMD_SSBD)) {
-		set_cpu_cap(c, X86_FEATURE_SSBD);
-		set_cpu_cap(c, X86_FEATURE_AMD_SSBD);
-	}
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index e23e289..9be7292 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -157,8 +157,8 @@ void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl)
 	if (!static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
 		return;
 
-	/* Intel controls SSB in MSR_SPEC_CTRL */
-	if (static_cpu_has(X86_FEATURE_SPEC_CTRL))
+	/* SSBD controlled in MSR_SPEC_CTRL */
+	if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD))
 		host |= ssbd_tif_to_spec_ctrl(current_thread_info()->flags);
 
 	if (host != guest_spec_ctrl)
@@ -174,8 +174,8 @@ void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl)
 	if (!static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
 		return;
 
-	/* Intel controls SSB in MSR_SPEC_CTRL */
-	if (static_cpu_has(X86_FEATURE_SPEC_CTRL))
+	/* SSBD controlled in MSR_SPEC_CTRL */
+	if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD))
 		host |= ssbd_tif_to_spec_ctrl(current_thread_info()->flags);
 
 	if (host != guest_spec_ctrl)
@@ -187,7 +187,7 @@ static void x86_amd_ssb_disable(void)
 {
 	u64 msrval = x86_amd_ls_cfg_base | x86_amd_ls_cfg_ssbd_mask;
 
-	if (boot_cpu_has(X86_FEATURE_AMD_SSBD))
+	if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD))
 		wrmsrl(MSR_AMD64_LS_CFG, msrval);
 }
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 1f70ff1..1097723 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -693,6 +693,9 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
 		set_cpu_cap(c, X86_FEATURE_STIBP);
 
+	if (cpu_has(c, X86_FEATURE_SPEC_CTRL_SSBD))
+		set_cpu_cap(c, X86_FEATURE_SSBD);
+
 	if (cpu_has(c, X86_FEATURE_AMD_IBRS)) {
 		set_cpu_cap(c, X86_FEATURE_IBRS);
 		set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 9a84e75..4dce22d 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -121,6 +121,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		setup_clear_cpu_cap(X86_FEATURE_MSR_SPEC_CTRL);
 		setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP);
 		setup_clear_cpu_cap(X86_FEATURE_SSBD);
+		setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL_SSBD);
 	}
 
 	/*
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 57d4ba2..8cefbd2 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -203,7 +203,7 @@ static __always_inline void __speculative_store_bypass_update(unsigned long tifn
 {
 	u64 msr;
 
-	if (static_cpu_has(X86_FEATURE_AMD_SSBD)) {
+	if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) {
 		msr = x86_amd_ls_cfg_base | ssbd_tif_to_amd_ls_cfg(tifn);
 		wrmsrl(MSR_AMD64_LS_CFG, msr);
 	} else {

[PATCH 4.4.y 090/101] x86/cpu/AMD: Fix erratum 1076 (CPB bit)

[Srivatsa S. Bhat]

From: Borislav Petkov <bp@suse.de>

commit f7f3dc00f61261cdc9ccd8b886f21bc4dffd6fd9 upstream

CPUID Fn8000_0007_EDX[CPB] is wrongly 0 on models up to B1. But they do
support CPB (AMD's Core Performance Boosting cpufreq CPU feature), so fix that.

Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sherry Hurwitz <sherry.hurwitz@amd.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170907170821.16021-1-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/amd.c |   11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index a97fd67..87f4a0d 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -713,6 +713,16 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 	}
 }
 
+static void init_amd_zn(struct cpuinfo_x86 *c)
+{
+	/*
+	 * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects
+	 * all up to and including B1.
+	 */
+	if (c->x86_model <= 1 && c->x86_mask <= 1)
+		set_cpu_cap(c, X86_FEATURE_CPB);
+}
+
 static void init_amd(struct cpuinfo_x86 *c)
 {
 	u32 dummy;
@@ -743,6 +753,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 	case 0x10: init_amd_gh(c); break;
 	case 0x12: init_amd_ln(c); break;
 	case 0x15: init_amd_bd(c); break;
+	case 0x17: init_amd_zn(c); break;
 	}
 
 	/* Enable workaround for FXSAVE leak */

[PATCH 4.4.y 091/101] x86/cpufeatures: Add FEATURE_ZEN

[Srivatsa S. Bhat]

From: Thomas Gleixner <tglx@linutronix.de>

commit d1035d971829dcf80e8686ccde26f94b0a069472 upstream

Add a ZEN feature bit so family-dependent static_cpu_has() optimizations
can be built for ZEN.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeatures.h |    2 ++
 arch/x86/kernel/cpu/amd.c          |    1 +
 2 files changed, 3 insertions(+)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 7dd1bba..8ae9132 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -213,6 +213,8 @@
 #define X86_FEATURE_IBRS	( 7*32+25) /* Indirect Branch Restricted Speculation */
 #define X86_FEATURE_IBPB	( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP	( 7*32+27) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_ZEN		( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
+
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 87f4a0d..9f61518 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -715,6 +715,7 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 
 static void init_amd_zn(struct cpuinfo_x86 *c)
 {
+	set_cpu_cap(c, X86_FEATURE_ZEN);
 	/*
 	 * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects
 	 * all up to and including B1.

[PATCH 4.4.y 092/101] x86/speculation: Handle HT correctly on AMD

[Srivatsa S. Bhat]

From: Thomas Gleixner <tglx@linutronix.de>

commit 1f50ddb4f4189243c05926b842dc1a0332195f31 upstream

The AMD64_LS_CFG MSR is a per core MSR on Family 17H CPUs. That means when
hyperthreading is enabled the SSBD bit toggle needs to take both cores into
account. Otherwise the following situation can happen:

CPU0		CPU1

disable SSB
		disable SSB
		enable  SSB <- Enables it for the Core, i.e. for CPU0 as well

So after the SSB enable on CPU1 the task on CPU0 runs with SSB enabled
again.

On Intel the SSBD control is per core as well, but the synchronization
logic is implemented behind the per thread SPEC_CTRL MSR. It works like
this:

  CORE_SPEC_CTRL = THREAD0_SPEC_CTRL | THREAD1_SPEC_CTRL

i.e. if one of the threads enables a mitigation then this affects both and
the mitigation is only disabled in the core when both threads disabled it.

Add the necessary synchronization logic for AMD family 17H. Unfortunately
that requires a spinlock to serialize the access to the MSR, but the locks
are only shared between siblings.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/spec-ctrl.h |    6 ++
 arch/x86/kernel/process.c        |  125 ++++++++++++++++++++++++++++++++++++--
 arch/x86/kernel/smpboot.c        |    5 ++
 3 files changed, 130 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
index dc21209..0cb49c4 100644
--- a/arch/x86/include/asm/spec-ctrl.h
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -33,6 +33,12 @@ static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn)
 	return (tifn & _TIF_SSBD) ? x86_amd_ls_cfg_ssbd_mask : 0ULL;
 }
 
+#ifdef CONFIG_SMP
+extern void speculative_store_bypass_ht_init(void);
+#else
+static inline void speculative_store_bypass_ht_init(void) { }
+#endif
+
 extern void speculative_store_bypass_update(void);
 
 #endif
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 8cefbd2..0842869 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -199,22 +199,135 @@ static inline void switch_to_bitmap(struct tss_struct *tss,
 	}
 }
 
-static __always_inline void __speculative_store_bypass_update(unsigned long tifn)
+#ifdef CONFIG_SMP
+
+struct ssb_state {
+	struct ssb_state	*shared_state;
+	raw_spinlock_t		lock;
+	unsigned int		disable_state;
+	unsigned long		local_state;
+};
+
+#define LSTATE_SSB	0
+
+static DEFINE_PER_CPU(struct ssb_state, ssb_state);
+
+void speculative_store_bypass_ht_init(void)
 {
-	u64 msr;
+	struct ssb_state *st = this_cpu_ptr(&ssb_state);
+	unsigned int this_cpu = smp_processor_id();
+	unsigned int cpu;
+
+	st->local_state = 0;
+
+	/*
+	 * Shared state setup happens once on the first bringup
+	 * of the CPU. It's not destroyed on CPU hotunplug.
+	 */
+	if (st->shared_state)
+		return;
+
+	raw_spin_lock_init(&st->lock);
 
-	if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) {
-		msr = x86_amd_ls_cfg_base | ssbd_tif_to_amd_ls_cfg(tifn);
+	/*
+	 * Go over HT siblings and check whether one of them has set up the
+	 * shared state pointer already.
+	 */
+	for_each_cpu(cpu, topology_sibling_cpumask(this_cpu)) {
+		if (cpu == this_cpu)
+			continue;
+
+		if (!per_cpu(ssb_state, cpu).shared_state)
+			continue;
+
+		/* Link it to the state of the sibling: */
+		st->shared_state = per_cpu(ssb_state, cpu).shared_state;
+		return;
+	}
+
+	/*
+	 * First HT sibling to come up on the core.  Link shared state of
+	 * the first HT sibling to itself. The siblings on the same core
+	 * which come up later will see the shared state pointer and link
+	 * themself to the state of this CPU.
+	 */
+	st->shared_state = st;
+}
+
+/*
+ * Logic is: First HT sibling enables SSBD for both siblings in the core
+ * and last sibling to disable it, disables it for the whole core. This how
+ * MSR_SPEC_CTRL works in "hardware":
+ *
+ *  CORE_SPEC_CTRL = THREAD0_SPEC_CTRL | THREAD1_SPEC_CTRL
+ */
+static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
+{
+	struct ssb_state *st = this_cpu_ptr(&ssb_state);
+	u64 msr = x86_amd_ls_cfg_base;
+
+	if (!static_cpu_has(X86_FEATURE_ZEN)) {
+		msr |= ssbd_tif_to_amd_ls_cfg(tifn);
 		wrmsrl(MSR_AMD64_LS_CFG, msr);
+		return;
+	}
+
+	if (tifn & _TIF_SSBD) {
+		/*
+		 * Since this can race with prctl(), block reentry on the
+		 * same CPU.
+		 */
+		if (__test_and_set_bit(LSTATE_SSB, &st->local_state))
+			return;
+
+		msr |= x86_amd_ls_cfg_ssbd_mask;
+
+		raw_spin_lock(&st->shared_state->lock);
+		/* First sibling enables SSBD: */
+		if (!st->shared_state->disable_state)
+			wrmsrl(MSR_AMD64_LS_CFG, msr);
+		st->shared_state->disable_state++;
+		raw_spin_unlock(&st->shared_state->lock);
 	} else {
-		msr = x86_spec_ctrl_base | ssbd_tif_to_spec_ctrl(tifn);
-		wrmsrl(MSR_IA32_SPEC_CTRL, msr);
+		if (!__test_and_clear_bit(LSTATE_SSB, &st->local_state))
+			return;
+
+		raw_spin_lock(&st->shared_state->lock);
+		st->shared_state->disable_state--;
+		if (!st->shared_state->disable_state)
+			wrmsrl(MSR_AMD64_LS_CFG, msr);
+		raw_spin_unlock(&st->shared_state->lock);
 	}
 }
+#else
+static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
+{
+	u64 msr = x86_amd_ls_cfg_base | ssbd_tif_to_amd_ls_cfg(tifn);
+
+	wrmsrl(MSR_AMD64_LS_CFG, msr);
+}
+#endif
+
+static __always_inline void intel_set_ssb_state(unsigned long tifn)
+{
+	u64 msr = x86_spec_ctrl_base | ssbd_tif_to_spec_ctrl(tifn);
+
+	wrmsrl(MSR_IA32_SPEC_CTRL, msr);
+}
+
+static __always_inline void __speculative_store_bypass_update(unsigned long tifn)
+{
+	if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD))
+		amd_set_core_ssb_state(tifn);
+	else
+		intel_set_ssb_state(tifn);
+}
 
 void speculative_store_bypass_update(void)
 {
+	preempt_disable();
 	__speculative_store_bypass_update(current_thread_info()->flags);
+	preempt_enable();
 }
 
 void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 1f7aefc..c017f1c 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -75,6 +75,7 @@
 #include <asm/i8259.h>
 #include <asm/realmode.h>
 #include <asm/misc.h>
+#include <asm/spec-ctrl.h>
 
 /* Number of siblings per CPU package */
 int smp_num_siblings = 1;
@@ -217,6 +218,8 @@ static void notrace start_secondary(void *unused)
 	 */
 	check_tsc_sync_target();
 
+	speculative_store_bypass_ht_init();
+
 	/*
 	 * Lock vector_lock and initialize the vectors on this cpu
 	 * before setting the cpu online. We must set it online with
@@ -1209,6 +1212,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	set_mtrr_aps_delayed_init();
 
 	smp_quirk_init_udelay();
+
+	speculative_store_bypass_ht_init();
 }
 
 void arch_enable_nonboot_cpus_begin(void)

[PATCH 4.4.y 093/101] x86/bugs, KVM: Extend speculation control for VIRT_SPEC_CTRL

[Srivatsa S. Bhat]

From: Thomas Gleixner <tglx@linutronix.de>

commit ccbcd2674472a978b48c91c1fbfb66c0ff959f24 upstream

AMD is proposing a VIRT_SPEC_CTRL MSR to handle the Speculative Store
Bypass Disable via MSR_AMD64_LS_CFG so that guests do not have to care
about the bit position of the SSBD bit and thus facilitate migration.
Also, the sibling coordination on Family 17H CPUs can only be done on
the host.

Extend x86_spec_ctrl_set_guest() and x86_spec_ctrl_restore_host() with an
extra argument for the VIRT_SPEC_CTRL MSR.

Hand in 0 from VMX and in SVM add a new virt_spec_ctrl member to the CPU
data structure which is going to be used in later patches for the actual
implementation.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Srivatsa: Backported to 4.4.y, skipping the KVM changes in this patch. ]
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/spec-ctrl.h |    9 ++++++---
 arch/x86/kernel/cpu/bugs.c       |   20 ++++++++++++++++++--
 2 files changed, 24 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
index 0cb49c4..6e28740 100644
--- a/arch/x86/include/asm/spec-ctrl.h
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -10,10 +10,13 @@
  * the guest has, while on VMEXIT we restore the host view. This
  * would be easier if SPEC_CTRL were architecturally maskable or
  * shadowable for guests but this is not (currently) the case.
- * Takes the guest view of SPEC_CTRL MSR as a parameter.
+ * Takes the guest view of SPEC_CTRL MSR as a parameter and also
+ * the guest's version of VIRT_SPEC_CTRL, if emulated.
  */
-extern void x86_spec_ctrl_set_guest(u64);
-extern void x86_spec_ctrl_restore_host(u64);
+extern void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl,
+				    u64 guest_virt_spec_ctrl);
+extern void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl,
+				       u64 guest_virt_spec_ctrl);
 
 /* AMD specific Speculative Store Bypass MSR data */
 extern u64 x86_amd_ls_cfg_base;
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 9be7292..a1c98fd 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -149,7 +149,15 @@ u64 x86_spec_ctrl_get_default(void)
 }
 EXPORT_SYMBOL_GPL(x86_spec_ctrl_get_default);
 
-void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl)
+/**
+ * x86_spec_ctrl_set_guest - Set speculation control registers for the guest
+ * @guest_spec_ctrl:		The guest content of MSR_SPEC_CTRL
+ * @guest_virt_spec_ctrl:	The guest controlled bits of MSR_VIRT_SPEC_CTRL
+ *				(may get translated to MSR_AMD64_LS_CFG bits)
+ *
+ * Avoids writing to the MSR if the content/bits are the same
+ */
+void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl)
 {
 	u64 host = x86_spec_ctrl_base;
 
@@ -166,7 +174,15 @@ void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl)
 }
 EXPORT_SYMBOL_GPL(x86_spec_ctrl_set_guest);
 
-void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl)
+/**
+ * x86_spec_ctrl_restore_host - Restore host speculation control registers
+ * @guest_spec_ctrl:		The guest content of MSR_SPEC_CTRL
+ * @guest_virt_spec_ctrl:	The guest controlled bits of MSR_VIRT_SPEC_CTRL
+ *				(may get translated to MSR_AMD64_LS_CFG bits)
+ *
+ * Avoids writing to the MSR if the content/bits are the same
+ */
+void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl)
 {
 	u64 host = x86_spec_ctrl_base;
 

[PATCH 4.4.y 094/101] x86/speculation: Add virtualized speculative store bypass disable support

[Srivatsa S. Bhat]

From: Tom Lendacky <thomas.lendacky@amd.com>

commit 11fb0683493b2da112cd64c9dada221b52463bf7 upstream

Some AMD processors only support a non-architectural means of enabling
speculative store bypass disable (SSBD).  To allow a simplified view of
this to a guest, an architectural definition has been created through a new
CPUID bit, 0x80000008_EBX[25], and a new MSR, 0xc001011f.  With this, a
hypervisor can virtualize the existence of this definition and provide an
architectural method for using SSBD to a guest.

Add the new CPUID feature, the new MSR and update the existing SSBD
support to use this MSR when present.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/cpufeatures.h |    1 +
 arch/x86/include/asm/msr-index.h   |    2 ++
 arch/x86/kernel/cpu/bugs.c         |    4 +++-
 arch/x86/kernel/process.c          |   13 ++++++++++++-
 4 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 8ae9132..f4b175d 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -269,6 +269,7 @@
 #define X86_FEATURE_AMD_IBPB	(13*32+12) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_AMD_IBRS	(13*32+14) /* Indirect Branch Restricted Speculation */
 #define X86_FEATURE_AMD_STIBP	(13*32+15) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_VIRT_SSBD	(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
 #define X86_FEATURE_DTHERM	(14*32+ 0) /* Digital Thermal Sensor */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 2ea2ff1..22f2dd5 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -328,6 +328,8 @@
 #define MSR_AMD64_IBSOPDATA4		0xc001103d
 #define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */
 
+#define MSR_AMD64_VIRT_SPEC_CTRL	0xc001011f
+
 /* Fam 16h MSRs */
 #define MSR_F16H_L2I_PERF_CTL		0xc0010230
 #define MSR_F16H_L2I_PERF_CTR		0xc0010231
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index a1c98fd..50ab206a 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -203,7 +203,9 @@ static void x86_amd_ssb_disable(void)
 {
 	u64 msrval = x86_amd_ls_cfg_base | x86_amd_ls_cfg_ssbd_mask;
 
-	if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD))
+	if (boot_cpu_has(X86_FEATURE_VIRT_SSBD))
+		wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, SPEC_CTRL_SSBD);
+	else if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD))
 		wrmsrl(MSR_AMD64_LS_CFG, msrval);
 }
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 0842869..eab9d0c 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -308,6 +308,15 @@ static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
 }
 #endif
 
+static __always_inline void amd_set_ssb_virt_state(unsigned long tifn)
+{
+	/*
+	 * SSBD has the same definition in SPEC_CTRL and VIRT_SPEC_CTRL,
+	 * so ssbd_tif_to_spec_ctrl() just works.
+	 */
+	wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, ssbd_tif_to_spec_ctrl(tifn));
+}
+
 static __always_inline void intel_set_ssb_state(unsigned long tifn)
 {
 	u64 msr = x86_spec_ctrl_base | ssbd_tif_to_spec_ctrl(tifn);
@@ -317,7 +326,9 @@ static __always_inline void intel_set_ssb_state(unsigned long tifn)
 
 static __always_inline void __speculative_store_bypass_update(unsigned long tifn)
 {
-	if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD))
+	if (static_cpu_has(X86_FEATURE_VIRT_SSBD))
+		amd_set_ssb_virt_state(tifn);
+	else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD))
 		amd_set_core_ssb_state(tifn);
 	else
 		intel_set_ssb_state(tifn);

[PATCH 4.4.y 095/101] x86/speculation: Rework speculative_store_bypass_update()

[Srivatsa S. Bhat]

From: Thomas Gleixner <tglx@linutronix.de>

commit 0270be3e34efb05a88bc4c422572ece038ef3608 upstream

The upcoming support for the virtual SPEC_CTRL MSR on AMD needs to reuse
speculative_store_bypass_update() to avoid code duplication. Add an
argument for supplying a thread info (TIF) value and create a wrapper
speculative_store_bypass_update_current() which is used at the existing
call site.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/spec-ctrl.h |    7 ++++++-
 arch/x86/kernel/cpu/bugs.c       |    2 +-
 arch/x86/kernel/process.c        |    4 ++--
 3 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
index 6e28740..82b6c5a 100644
--- a/arch/x86/include/asm/spec-ctrl.h
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -42,6 +42,11 @@ extern void speculative_store_bypass_ht_init(void);
 static inline void speculative_store_bypass_ht_init(void) { }
 #endif
 
-extern void speculative_store_bypass_update(void);
+extern void speculative_store_bypass_update(unsigned long tif);
+
+static inline void speculative_store_bypass_update_current(void)
+{
+	speculative_store_bypass_update(current_thread_info()->flags);
+}
 
 #endif
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 50ab206a..1b29be9 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -596,7 +596,7 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
 	 * mitigation until it is next scheduled.
 	 */
 	if (task == current && update)
-		speculative_store_bypass_update();
+		speculative_store_bypass_update_current();
 
 	return 0;
 }
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index eab9d0c..e18c879 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -334,10 +334,10 @@ static __always_inline void __speculative_store_bypass_update(unsigned long tifn
 		intel_set_ssb_state(tifn);
 }
 
-void speculative_store_bypass_update(void)
+void speculative_store_bypass_update(unsigned long tif)
 {
 	preempt_disable();
-	__speculative_store_bypass_update(current_thread_info()->flags);
+	__speculative_store_bypass_update(tif);
 	preempt_enable();
 }
 

[PATCH 4.4.y 096/101] x86/bugs: Unify x86_spec_ctrl_{set_guest, restore_host}

[Srivatsa S. Bhat]

From: Borislav Petkov <bp@suse.de>

commit cc69b34989210f067b2c51d5539b5f96ebcc3a01 upstream

Function bodies are very similar and are going to grow more almost
identical code. Add a bool arg to determine whether SPEC_CTRL is being set
for the guest or restored to the host.

No functional changes.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/spec-ctrl.h |   33 ++++++++++++++++++---
 arch/x86/kernel/cpu/bugs.c       |   60 ++++++++++----------------------------
 2 files changed, 44 insertions(+), 49 deletions(-)

diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
index 82b6c5a..9cecbe5 100644
--- a/arch/x86/include/asm/spec-ctrl.h
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -13,10 +13,35 @@
  * Takes the guest view of SPEC_CTRL MSR as a parameter and also
  * the guest's version of VIRT_SPEC_CTRL, if emulated.
  */
-extern void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl,
-				    u64 guest_virt_spec_ctrl);
-extern void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl,
-				       u64 guest_virt_spec_ctrl);
+extern void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool guest);
+
+/**
+ * x86_spec_ctrl_set_guest - Set speculation control registers for the guest
+ * @guest_spec_ctrl:		The guest content of MSR_SPEC_CTRL
+ * @guest_virt_spec_ctrl:	The guest controlled bits of MSR_VIRT_SPEC_CTRL
+ *				(may get translated to MSR_AMD64_LS_CFG bits)
+ *
+ * Avoids writing to the MSR if the content/bits are the same
+ */
+static inline
+void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl)
+{
+	x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, true);
+}
+
+/**
+ * x86_spec_ctrl_restore_host - Restore host speculation control registers
+ * @guest_spec_ctrl:		The guest content of MSR_SPEC_CTRL
+ * @guest_virt_spec_ctrl:	The guest controlled bits of MSR_VIRT_SPEC_CTRL
+ *				(may get translated to MSR_AMD64_LS_CFG bits)
+ *
+ * Avoids writing to the MSR if the content/bits are the same
+ */
+static inline
+void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl)
+{
+	x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, false);
+}
 
 /* AMD specific Speculative Store Bypass MSR data */
 extern u64 x86_amd_ls_cfg_base;
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 1b29be9..208d44c 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -149,55 +149,25 @@ u64 x86_spec_ctrl_get_default(void)
 }
 EXPORT_SYMBOL_GPL(x86_spec_ctrl_get_default);
 
-/**
- * x86_spec_ctrl_set_guest - Set speculation control registers for the guest
- * @guest_spec_ctrl:		The guest content of MSR_SPEC_CTRL
- * @guest_virt_spec_ctrl:	The guest controlled bits of MSR_VIRT_SPEC_CTRL
- *				(may get translated to MSR_AMD64_LS_CFG bits)
- *
- * Avoids writing to the MSR if the content/bits are the same
- */
-void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl)
+void
+x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
 {
-	u64 host = x86_spec_ctrl_base;
+	struct thread_info *ti = current_thread_info();
+	u64 msr, host = x86_spec_ctrl_base;
 
 	/* Is MSR_SPEC_CTRL implemented ? */
-	if (!static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
-		return;
-
-	/* SSBD controlled in MSR_SPEC_CTRL */
-	if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD))
-		host |= ssbd_tif_to_spec_ctrl(current_thread_info()->flags);
-
-	if (host != guest_spec_ctrl)
-		wrmsrl(MSR_IA32_SPEC_CTRL, guest_spec_ctrl);
-}
-EXPORT_SYMBOL_GPL(x86_spec_ctrl_set_guest);
-
-/**
- * x86_spec_ctrl_restore_host - Restore host speculation control registers
- * @guest_spec_ctrl:		The guest content of MSR_SPEC_CTRL
- * @guest_virt_spec_ctrl:	The guest controlled bits of MSR_VIRT_SPEC_CTRL
- *				(may get translated to MSR_AMD64_LS_CFG bits)
- *
- * Avoids writing to the MSR if the content/bits are the same
- */
-void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl)
-{
-	u64 host = x86_spec_ctrl_base;
-
-	/* Is MSR_SPEC_CTRL implemented ? */
-	if (!static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
-		return;
-
-	/* SSBD controlled in MSR_SPEC_CTRL */
-	if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD))
-		host |= ssbd_tif_to_spec_ctrl(current_thread_info()->flags);
-
-	if (host != guest_spec_ctrl)
-		wrmsrl(MSR_IA32_SPEC_CTRL, host);
+	if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) {
+		/* SSBD controlled in MSR_SPEC_CTRL */
+		if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD))
+			host |= ssbd_tif_to_spec_ctrl(ti->flags);
+
+		if (host != guest_spec_ctrl) {
+			msr = setguest ? guest_spec_ctrl : host;
+			wrmsrl(MSR_IA32_SPEC_CTRL, msr);
+		}
+	}
 }
-EXPORT_SYMBOL_GPL(x86_spec_ctrl_restore_host);
+EXPORT_SYMBOL_GPL(x86_virt_spec_ctrl);
 
 static void x86_amd_ssb_disable(void)
 {

[PATCH 4.4.y 097/101] x86/bugs: Expose x86_spec_ctrl_base directly

[Srivatsa S. Bhat]

From: Thomas Gleixner <tglx@linutronix.de>

commit fa8ac4988249c38476f6ad678a4848a736373403 upstream

x86_spec_ctrl_base is the system wide default value for the SPEC_CTRL MSR.
x86_spec_ctrl_get_default() returns x86_spec_ctrl_base and was intended to
prevent modification to that variable. Though the variable is read only
after init and globaly visible already.

Remove the function and export the variable instead.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/nospec-branch.h |   16 +++++-----------
 arch/x86/include/asm/spec-ctrl.h     |    3 ---
 arch/x86/kernel/cpu/bugs.c           |   11 +----------
 3 files changed, 6 insertions(+), 24 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 640c11b..2757c79 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -172,16 +172,7 @@ enum spectre_v2_mitigation {
 	SPECTRE_V2_IBRS,
 };
 
-/*
- * The Intel specification for the SPEC_CTRL MSR requires that we
- * preserve any already set reserved bits at boot time (e.g. for
- * future additions that this kernel is not currently aware of).
- * We then set any additional mitigation bits that we want
- * ourselves and always use this as the base for SPEC_CTRL.
- * We also use this when handling guest entry/exit as below.
- */
 extern void x86_spec_ctrl_set(u64);
-extern u64 x86_spec_ctrl_get_default(void);
 
 /* The Speculative Store Bypass disable variants */
 enum ssb_mitigation {
@@ -232,6 +223,9 @@ static inline void indirect_branch_prediction_barrier(void)
 	alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB);
 }
 
+/* The Intel SPEC CTRL MSR base value cache */
+extern u64 x86_spec_ctrl_base;
+
 /*
  * With retpoline, we must use IBRS to restrict branch prediction
  * before calling into firmware.
@@ -240,7 +234,7 @@ static inline void indirect_branch_prediction_barrier(void)
  */
 #define firmware_restrict_branch_speculation_start()			\
 do {									\
-	u64 val = x86_spec_ctrl_get_default() | SPEC_CTRL_IBRS;		\
+	u64 val = x86_spec_ctrl_base | SPEC_CTRL_IBRS;			\
 									\
 	preempt_disable();						\
 	alternative_msr_write(MSR_IA32_SPEC_CTRL, val,			\
@@ -249,7 +243,7 @@ do {									\
 
 #define firmware_restrict_branch_speculation_end()			\
 do {									\
-	u64 val = x86_spec_ctrl_get_default();				\
+	u64 val = x86_spec_ctrl_base;					\
 									\
 	alternative_msr_write(MSR_IA32_SPEC_CTRL, val,			\
 			      X86_FEATURE_USE_IBRS_FW);			\
diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
index 9cecbe5..763d497 100644
--- a/arch/x86/include/asm/spec-ctrl.h
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -47,9 +47,6 @@ void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl)
 extern u64 x86_amd_ls_cfg_base;
 extern u64 x86_amd_ls_cfg_ssbd_mask;
 
-/* The Intel SPEC CTRL MSR base value cache */
-extern u64 x86_spec_ctrl_base;
-
 static inline u64 ssbd_tif_to_spec_ctrl(u64 tifn)
 {
 	BUILD_BUG_ON(TIF_SSBD < SPEC_CTRL_SSBD_SHIFT);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 208d44c..5391df5 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -35,6 +35,7 @@ static void __init ssb_select_mitigation(void);
  * writes to SPEC_CTRL contain whatever reserved bits have been set.
  */
 u64 x86_spec_ctrl_base;
+EXPORT_SYMBOL_GPL(x86_spec_ctrl_base);
 
 /*
  * The vendor and possibly platform specific bits which can be modified in
@@ -139,16 +140,6 @@ void x86_spec_ctrl_set(u64 val)
 }
 EXPORT_SYMBOL_GPL(x86_spec_ctrl_set);
 
-u64 x86_spec_ctrl_get_default(void)
-{
-	u64 msrval = x86_spec_ctrl_base;
-
-	if (static_cpu_has(X86_FEATURE_SPEC_CTRL))
-		msrval |= ssbd_tif_to_spec_ctrl(current_thread_info()->flags);
-	return msrval;
-}
-EXPORT_SYMBOL_GPL(x86_spec_ctrl_get_default);
-
 void
 x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
 {

[PATCH 4.4.y 098/101] x86/bugs: Remove x86_spec_ctrl_set()

[Srivatsa S. Bhat]

From: Thomas Gleixner <tglx@linutronix.de>

commit 4b59bdb569453a60b752b274ca61f009e37f4dae upstream

x86_spec_ctrl_set() is only used in bugs.c and the extra mask checks there
provide no real value as both call sites can just write x86_spec_ctrl_base
to MSR_SPEC_CTRL. x86_spec_ctrl_base is valid and does not need any extra
masking or checking.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/nospec-branch.h |    2 --
 arch/x86/kernel/cpu/bugs.c           |   13 ++-----------
 2 files changed, 2 insertions(+), 13 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 2757c79..b4c74c2 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -172,8 +172,6 @@ enum spectre_v2_mitigation {
 	SPECTRE_V2_IBRS,
 };
 
-extern void x86_spec_ctrl_set(u64);
-
 /* The Speculative Store Bypass disable variants */
 enum ssb_mitigation {
 	SPEC_STORE_BYPASS_NONE,
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 5391df5..05eed68 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -131,15 +131,6 @@ static const char *spectre_v2_strings[] = {
 
 static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE;
 
-void x86_spec_ctrl_set(u64 val)
-{
-	if (val & x86_spec_ctrl_mask)
-		WARN_ONCE(1, "SPEC_CTRL MSR value 0x%16llx is unknown.\n", val);
-	else
-		wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base | val);
-}
-EXPORT_SYMBOL_GPL(x86_spec_ctrl_set);
-
 void
 x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
 {
@@ -501,7 +492,7 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
 		case X86_VENDOR_INTEL:
 			x86_spec_ctrl_base |= SPEC_CTRL_SSBD;
 			x86_spec_ctrl_mask &= ~SPEC_CTRL_SSBD;
-			x86_spec_ctrl_set(SPEC_CTRL_SSBD);
+			wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
 			break;
 		case X86_VENDOR_AMD:
 			x86_amd_ssb_disable();
@@ -613,7 +604,7 @@ int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
 void x86_spec_ctrl_setup_ap(void)
 {
 	if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
-		x86_spec_ctrl_set(x86_spec_ctrl_base & ~x86_spec_ctrl_mask);
+		wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
 
 	if (ssb_mode == SPEC_STORE_BYPASS_DISABLE)
 		x86_amd_ssb_disable();

[PATCH 4.4.y 099/101] x86/bugs: Rework spec_ctrl base and mask logic

[Srivatsa S. Bhat]

From: Thomas Gleixner <tglx@linutronix.de>

commit be6fcb5478e95bb1c91f489121238deb3abca46a upstream

x86_spec_ctrL_mask is intended to mask out bits from a MSR_SPEC_CTRL value
which are not to be modified. However the implementation is not really used
and the bitmask was inverted to make a check easier, which was removed in
"x86/bugs: Remove x86_spec_ctrl_set()"

Aside of that it is missing the STIBP bit if it is supported by the
platform, so if the mask would be used in x86_virt_spec_ctrl() then it
would prevent a guest from setting STIBP.

Add the STIBP bit if supported and use the mask in x86_virt_spec_ctrl() to
sanitize the value which is supplied by the guest.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/kernel/cpu/bugs.c |   26 +++++++++++++++++++-------
 1 file changed, 19 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 05eed68..af11a02 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -41,7 +41,7 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_base);
  * The vendor and possibly platform specific bits which can be modified in
  * x86_spec_ctrl_base.
  */
-static u64 x86_spec_ctrl_mask = ~SPEC_CTRL_IBRS;
+static u64 x86_spec_ctrl_mask = SPEC_CTRL_IBRS;
 
 /*
  * AMD specific MSR info for Speculative Store Bypass control.
@@ -67,6 +67,10 @@ void __init check_bugs(void)
 	if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
 		rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
 
+	/* Allow STIBP in MSR_SPEC_CTRL if supported */
+	if (boot_cpu_has(X86_FEATURE_STIBP))
+		x86_spec_ctrl_mask |= SPEC_CTRL_STIBP;
+
 	/* Select the proper spectre mitigation before patching alternatives */
 	spectre_v2_select_mitigation();
 
@@ -134,18 +138,26 @@ static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE;
 void
 x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
 {
+	u64 msrval, guestval, hostval = x86_spec_ctrl_base;
 	struct thread_info *ti = current_thread_info();
-	u64 msr, host = x86_spec_ctrl_base;
 
 	/* Is MSR_SPEC_CTRL implemented ? */
 	if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) {
+		/*
+		 * Restrict guest_spec_ctrl to supported values. Clear the
+		 * modifiable bits in the host base value and or the
+		 * modifiable bits from the guest value.
+		 */
+		guestval = hostval & ~x86_spec_ctrl_mask;
+		guestval |= guest_spec_ctrl & x86_spec_ctrl_mask;
+
 		/* SSBD controlled in MSR_SPEC_CTRL */
 		if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD))
-			host |= ssbd_tif_to_spec_ctrl(ti->flags);
+			hostval |= ssbd_tif_to_spec_ctrl(ti->flags);
 
-		if (host != guest_spec_ctrl) {
-			msr = setguest ? guest_spec_ctrl : host;
-			wrmsrl(MSR_IA32_SPEC_CTRL, msr);
+		if (hostval != guestval) {
+			msrval = setguest ? guestval : hostval;
+			wrmsrl(MSR_IA32_SPEC_CTRL, msrval);
 		}
 	}
 }
@@ -491,7 +503,7 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
 		switch (boot_cpu_data.x86_vendor) {
 		case X86_VENDOR_INTEL:
 			x86_spec_ctrl_base |= SPEC_CTRL_SSBD;
-			x86_spec_ctrl_mask &= ~SPEC_CTRL_SSBD;
+			x86_spec_ctrl_mask |= SPEC_CTRL_SSBD;
 			wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
 			break;
 		case X86_VENDOR_AMD:

[PATCH 4.4.y 100/101] x86/speculation, KVM: Implement support for VIRT_SPEC_CTRL/LS_CFG

[Srivatsa S. Bhat]

From: Thomas Gleixner <tglx@linutronix.de>

commit 47c61b3955cf712cadfc25635bf9bc174af030ea upstream

Add the necessary logic for supporting the emulated VIRT_SPEC_CTRL MSR to
x86_virt_spec_ctrl().  If either X86_FEATURE_LS_CFG_SSBD or
X86_FEATURE_VIRT_SPEC_CTRL is set then use the new guest_virt_spec_ctrl
argument to check whether the state must be modified on the host. The
update reuses speculative_store_bypass_update() so the ZEN-specific sibling
coordination can be reused.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/spec-ctrl.h |    6 ++++++
 arch/x86/kernel/cpu/bugs.c       |   30 ++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+)

diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
index 763d497..ae7c2c5 100644
--- a/arch/x86/include/asm/spec-ctrl.h
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -53,6 +53,12 @@ static inline u64 ssbd_tif_to_spec_ctrl(u64 tifn)
 	return (tifn & _TIF_SSBD) >> (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT);
 }
 
+static inline unsigned long ssbd_spec_ctrl_to_tif(u64 spec_ctrl)
+{
+	BUILD_BUG_ON(TIF_SSBD < SPEC_CTRL_SSBD_SHIFT);
+	return (spec_ctrl & SPEC_CTRL_SSBD) << (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT);
+}
+
 static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn)
 {
 	return (tifn & _TIF_SSBD) ? x86_amd_ls_cfg_ssbd_mask : 0ULL;
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index af11a02..12a8867 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -160,6 +160,36 @@ x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
 			wrmsrl(MSR_IA32_SPEC_CTRL, msrval);
 		}
 	}
+
+	/*
+	 * If SSBD is not handled in MSR_SPEC_CTRL on AMD, update
+	 * MSR_AMD64_L2_CFG or MSR_VIRT_SPEC_CTRL if supported.
+	 */
+	if (!static_cpu_has(X86_FEATURE_LS_CFG_SSBD) &&
+	    !static_cpu_has(X86_FEATURE_VIRT_SSBD))
+		return;
+
+	/*
+	 * If the host has SSBD mitigation enabled, force it in the host's
+	 * virtual MSR value. If its not permanently enabled, evaluate
+	 * current's TIF_SSBD thread flag.
+	 */
+	if (static_cpu_has(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE))
+		hostval = SPEC_CTRL_SSBD;
+	else
+		hostval = ssbd_tif_to_spec_ctrl(ti->flags);
+
+	/* Sanitize the guest value */
+	guestval = guest_virt_spec_ctrl & SPEC_CTRL_SSBD;
+
+	if (hostval != guestval) {
+		unsigned long tif;
+
+		tif = setguest ? ssbd_spec_ctrl_to_tif(guestval) :
+				 ssbd_spec_ctrl_to_tif(hostval);
+
+		speculative_store_bypass_update(tif);
+	}
 }
 EXPORT_SYMBOL_GPL(x86_virt_spec_ctrl);
 

[PATCH 4.4.y 101/101] x86/bugs: Rename SSBD_NO to SSB_NO

[Srivatsa S. Bhat]

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

commit 240da953fcc6a9008c92fae5b1f727ee5ed167ab upstream

The "336996 Speculative Execution Side Channel Mitigations" from
May defines this as SSB_NO, hence lets sync-up.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
---

 arch/x86/include/asm/msr-index.h |    2 +-
 arch/x86/kernel/cpu/common.c     |    2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 22f2dd5..caa0019 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -58,7 +58,7 @@
 #define MSR_IA32_ARCH_CAPABILITIES	0x0000010a
 #define ARCH_CAP_RDCL_NO		(1 << 0)   /* Not susceptible to Meltdown */
 #define ARCH_CAP_IBRS_ALL		(1 << 1)   /* Enhanced IBRS support */
-#define ARCH_CAP_SSBD_NO		(1 << 4)   /*
+#define ARCH_CAP_SSB_NO			(1 << 4)   /*
 						    * Not susceptible to Speculative Store Bypass
 						    * attack, so no Speculative Store Bypass
 						    * control required.
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 1097723..9ad38ad 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -881,7 +881,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
 
 	if (!x86_match_cpu(cpu_no_spec_store_bypass) &&
-	   !(ia32_cap & ARCH_CAP_SSBD_NO))
+	   !(ia32_cap & ARCH_CAP_SSB_NO))
 		setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
 
 	if (x86_match_cpu(cpu_no_speculation))

Re: [RESEND] Spectre-v2 (IBPB/IBRS) and SSBD fixes for 4.4.y

[Greg KH]

On Sat, Jul 14, 2018 at 02:25:43AM -0700, Srivatsa S. Bhat wrote:
> Hi Greg,
> 
> This patch series is a backport of the Spectre-v2 fixes (IBPB/IBRS)
> and patches for the Speculative Store Bypass vulnerability to 4.4.y
> (they apply cleanly on top of 4.4.140).
> 
> I used 4.9.y as my reference when backporting to 4.4.y (as I thought
> that would minimize the amount of fixing up necessary). Unfortunately
> I had to skip the KVM fixes for these vulnerabilities, as the KVM
> codebase is drastically different in 4.4 as compared to 4.9. (I tried
> my best to backport them initially, but wasn't confident that they
> were correct, so I decided to drop them from this series).
> 
> You'll notice that the initial few patches in this series include
> cleanups etc., that are non-critical to IBPB/IBRS/SSBD. Most of these
> patches are aimed at getting the cpufeature.h vs cpufeatures.h split
> into 4.4, since a lot of the subsequent patches update these headers.
> On my first attempt to backport these patches to 4.4.y, I had actually
> tried to do all the updates on the cpufeature.h file itself, but it
> started getting very cumbersome, so I resorted to backporting the
> cpufeature.h vs cpufeatures.h split and their dependencies as well. I
> think apart from these initial patches, the rest of the patchset
> doesn't have all that much noise. 

I've applied the "initial" patches to the 4.4-stable queue right now, as
those were all just "housekeeping" stuff.  I'll let others review the
rest of the series this week and see if anyone objects before throwing
them at the test-bots.

Many thanks for doing all of this work.

greg k-h

Re: [RESEND] Spectre-v2 (IBPB/IBRS) and SSBD fixes for 4.4.y

[Srivatsa S. Bhat]

On 7/15/18 4:26 AM, Greg KH wrote:
> On Sat, Jul 14, 2018 at 02:25:43AM -0700, Srivatsa S. Bhat wrote:
>> Hi Greg,
>>
>> This patch series is a backport of the Spectre-v2 fixes (IBPB/IBRS)
>> and patches for the Speculative Store Bypass vulnerability to 4.4.y
>> (they apply cleanly on top of 4.4.140).
>>
>> I used 4.9.y as my reference when backporting to 4.4.y (as I thought
>> that would minimize the amount of fixing up necessary). Unfortunately
>> I had to skip the KVM fixes for these vulnerabilities, as the KVM
>> codebase is drastically different in 4.4 as compared to 4.9. (I tried
>> my best to backport them initially, but wasn't confident that they
>> were correct, so I decided to drop them from this series).
>>
>> You'll notice that the initial few patches in this series include
>> cleanups etc., that are non-critical to IBPB/IBRS/SSBD. Most of these
>> patches are aimed at getting the cpufeature.h vs cpufeatures.h split
>> into 4.4, since a lot of the subsequent patches update these headers.
>> On my first attempt to backport these patches to 4.4.y, I had actually
>> tried to do all the updates on the cpufeature.h file itself, but it
>> started getting very cumbersome, so I resorted to backporting the
>> cpufeature.h vs cpufeatures.h split and their dependencies as well. I
>> think apart from these initial patches, the rest of the patchset
>> doesn't have all that much noise. 
> 
> I've applied the "initial" patches to the 4.4-stable queue right now, as
> those were all just "housekeeping" stuff.  I'll let others review the
> rest of the series this week and see if anyone objects before throwing
> them at the test-bots.
> 

Sounds great! Thanks a lot!

> Many thanks for doing all of this work.
> 

Thank you Greg!
 
Regards,
Srivatsa
VMware Photon OS

Re: [RESEND] Spectre-v2 (IBPB/IBRS) and SSBD fixes for 4.4.y

[Greg KH]

On Sat, Jul 14, 2018 at 02:25:43AM -0700, Srivatsa S. Bhat wrote:
> Hi Greg,
> 
> This patch series is a backport of the Spectre-v2 fixes (IBPB/IBRS)
> and patches for the Speculative Store Bypass vulnerability to 4.4.y
> (they apply cleanly on top of 4.4.140).
> 
> I used 4.9.y as my reference when backporting to 4.4.y (as I thought
> that would minimize the amount of fixing up necessary). Unfortunately
> I had to skip the KVM fixes for these vulnerabilities, as the KVM
> codebase is drastically different in 4.4 as compared to 4.9. (I tried
> my best to backport them initially, but wasn't confident that they
> were correct, so I decided to drop them from this series).
> 
> You'll notice that the initial few patches in this series include
> cleanups etc., that are non-critical to IBPB/IBRS/SSBD. Most of these
> patches are aimed at getting the cpufeature.h vs cpufeatures.h split
> into 4.4, since a lot of the subsequent patches update these headers.
> On my first attempt to backport these patches to 4.4.y, I had actually
> tried to do all the updates on the cpufeature.h file itself, but it
> started getting very cumbersome, so I resorted to backporting the
> cpufeature.h vs cpufeatures.h split and their dependencies as well. I
> think apart from these initial patches, the rest of the patchset
> doesn't have all that much noise. 
> 
> This patchset has been tested on both Intel and AMD machines (Intel
> Xeon CPU E5-2660 v4 and AMD EPYC 7281 16-Core Processor, respectively)
> with updated microcode. All the patch backports have been
> independently reviewed by Matt Helsley, Alexey Makhalov and Bo Gan.
> 
> I would appreciate if you could kindly consider these patches for
> review and inclusion in a future 4.4.y release.

Given no one has complained about these yet, I've queued them all up,
including the 2 extra ones you sent afterward.

Let's see what breaks :)

thanks,

greg k-h

Re: [RESEND] Spectre-v2 (IBPB/IBRS) and SSBD fixes for 4.4.y

[Srivatsa S. Bhat]

On 7/23/18 4:26 AM, Greg KH wrote:
> On Sat, Jul 14, 2018 at 02:25:43AM -0700, Srivatsa S. Bhat wrote:
>> Hi Greg,
>>
>> This patch series is a backport of the Spectre-v2 fixes (IBPB/IBRS)
>> and patches for the Speculative Store Bypass vulnerability to 4.4.y
>> (they apply cleanly on top of 4.4.140).
>>
>> I used 4.9.y as my reference when backporting to 4.4.y (as I thought
>> that would minimize the amount of fixing up necessary). Unfortunately
>> I had to skip the KVM fixes for these vulnerabilities, as the KVM
>> codebase is drastically different in 4.4 as compared to 4.9. (I tried
>> my best to backport them initially, but wasn't confident that they
>> were correct, so I decided to drop them from this series).
>>
>> You'll notice that the initial few patches in this series include
>> cleanups etc., that are non-critical to IBPB/IBRS/SSBD. Most of these
>> patches are aimed at getting the cpufeature.h vs cpufeatures.h split
>> into 4.4, since a lot of the subsequent patches update these headers.
>> On my first attempt to backport these patches to 4.4.y, I had actually
>> tried to do all the updates on the cpufeature.h file itself, but it
>> started getting very cumbersome, so I resorted to backporting the
>> cpufeature.h vs cpufeatures.h split and their dependencies as well. I
>> think apart from these initial patches, the rest of the patchset
>> doesn't have all that much noise. 
>>
>> This patchset has been tested on both Intel and AMD machines (Intel
>> Xeon CPU E5-2660 v4 and AMD EPYC 7281 16-Core Processor, respectively)
>> with updated microcode. All the patch backports have been
>> independently reviewed by Matt Helsley, Alexey Makhalov and Bo Gan.
>>
>> I would appreciate if you could kindly consider these patches for
>> review and inclusion in a future 4.4.y release.
> 
> Given no one has complained about these yet, I've queued them all up,
> including the 2 extra ones you sent afterward.
>
Great! Thank you very much!

> Let's see what breaks :)
> 

Hehe :)

Regards,
Srivatsa
VMware Photon OS

Re: [RESEND] Spectre-v2 (IBPB/IBRS) and SSBD fixes for 4.4.y

[Srivatsa S. Bhat]

On 7/23/18 3:06 PM, Jiri Kosina wrote:
> On Sat, 14 Jul 2018, Srivatsa S. Bhat wrote:
> 
>> This patch series is a backport of the Spectre-v2 fixes (IBPB/IBRS)
>> and patches for the Speculative Store Bypass vulnerability to 4.4.y
>> (they apply cleanly on top of 4.4.140).
> 
> FWIW -- not sure how much inspiration you took from our SLE 4.4-based 
> tree, but most of the stuff is already there for quite some time 
> (including the non-upstream IBRS on kernel boundary on SKL+, trampoline 
> stack for PTI (which the original port didn't have), etc).
> 
> The IBRS SKL+ stuff has not been picked up by Greg, as it's non-upstream, 
> and the trampoline stack I believe was pointed out to stable@, but noone 
> really sat down and did the port (our codebase is different than 4.4.x 
> stable base), but it definitely should be done if someone has to put 100% 
> trust into the PTI port (either that, or at least zeroing out the kernel 
> thread thread stack ... we used to have temporarily that before we 
> switched over to proper entry trampoline in this version as well).
> 

I did glance at the SLES 4.4 kernel sometime ago, but there seemed to
be way too many custom patches and I wasn't sure in what ways your
PTI/Spectre fixes depended on the other (x86) patches in your tree. So
I decided to backport entirely from the 4.9 stable tree instead. My
reasoning was that, since the 4.9 stable patches were trusted to work
well, their 4.4 backports should work well too, as long as they are
backported correctly.
 
However, if you are proposing that you'd like to contribute the
enhanced PTI/Spectre (upstream) patches from the SLES 4.4 tree to 4.4
stable, and have them merged instead of this patch series, then I
would certainly welcome it!

Regards,
Srivatsa
VMware Photon OS

Re: [RESEND] Spectre-v2 (IBPB/IBRS) and SSBD fixes for 4.4.y

[Jiri Kosina]

On Tue, 24 Jul 2018, Srivatsa S. Bhat wrote:

> However, if you are proposing that you'd like to contribute the enhanced 
> PTI/Spectre (upstream) patches from the SLES 4.4 tree to 4.4 stable, and 
> have them merged instead of this patch series, then I would certainly 
> welcome it!

I'd in principle love us to push everything back to 4.4, but there are a 
few reasons (*) why that's not happening shortly.

Anyway, to point out explicitly what's really needed for those folks 
running 4.4-stable and relying on PTI providing The Real Thing(TM), it's 
either a 4.4-stable port of

	http://kernel.suse.com/cgit/kernel-source/plain/patches.suse/x86-entry-64-use-a-per-cpu-trampoline-stack.patch?id=3428a77b02b1ba03e45d8fc352ec350429f57fc7

or making THREADINFO_GFP imply __GFP_ZERO.

(*) IBRS is not upstream, we historically have had very different x86 
    codebase compared to either 4.4, 4.4-stable or current Linus' tree, 
    and there are simply too many things happening right now to give this 
    high enough priority, sadly. We're not fully-dependent downstream 
    consumer of -stable any more, so this is one of the expected outcomes, 
    unfortunately; we don't immediately benefit from pushing our 
    downstream changes to stable, as we have to carry those over forward
    ourselves anyway.

Thanks,

-- 
Jiri Kosina
SUSE Labs

Re: [RESEND] Spectre-v2 (IBPB/IBRS) and SSBD fixes for 4.4.y

[Kees Cook]

On Tue, Jul 24, 2018 at 3:02 PM, Jiri Kosina <jikos@kernel.org> wrote:
> On Tue, 24 Jul 2018, Srivatsa S. Bhat wrote:
>
>> However, if you are proposing that you'd like to contribute the enhanced
>> PTI/Spectre (upstream) patches from the SLES 4.4 tree to 4.4 stable, and
>> have them merged instead of this patch series, then I would certainly
>> welcome it!
>
> I'd in principle love us to push everything back to 4.4, but there are a
> few reasons (*) why that's not happening shortly.
>
> Anyway, to point out explicitly what's really needed for those folks
> running 4.4-stable and relying on PTI providing The Real Thing(TM), it's
> either a 4.4-stable port of
>
>         http://kernel.suse.com/cgit/kernel-source/plain/patches.suse/x86-entry-64-use-a-per-cpu-trampoline-stack.patch?id=3428a77b02b1ba03e45d8fc352ec350429f57fc7
>
> or making THREADINFO_GFP imply __GFP_ZERO.

This is true in Linus's tree now. Should be trivial to backport:
https://git.kernel.org/linus/e01e80634ecdd

-Kees

-- 
Kees Cook
Pixel Security

Re: [RESEND] Spectre-v2 (IBPB/IBRS) and SSBD fixes for 4.4.y

[Srivatsa S. Bhat]

[-- Attachment #1: Type: text/plain, Size: 1379 bytes --]

On 7/26/18 4:09 PM, Kees Cook wrote:
> On Tue, Jul 24, 2018 at 3:02 PM, Jiri Kosina <jikos@kernel.org> wrote:
>> On Tue, 24 Jul 2018, Srivatsa S. Bhat wrote:
>>
>>> However, if you are proposing that you'd like to contribute the enhanced
>>> PTI/Spectre (upstream) patches from the SLES 4.4 tree to 4.4 stable, and
>>> have them merged instead of this patch series, then I would certainly
>>> welcome it!
>>
>> I'd in principle love us to push everything back to 4.4, but there are a
>> few reasons (*) why that's not happening shortly.
>>
>> Anyway, to point out explicitly what's really needed for those folks
>> running 4.4-stable and relying on PTI providing The Real Thing(TM), it's
>> either a 4.4-stable port of
>>
>>         http://kernel.suse.com/cgit/kernel-source/plain/patches.suse/x86-entry-64-use-a-per-cpu-trampoline-stack.patch?id=3428a77b02b1ba03e45d8fc352ec350429f57fc7
>>
>> or making THREADINFO_GFP imply __GFP_ZERO.
> 
> This is true in Linus's tree now. Should be trivial to backport:
> https://git.kernel.org/linus/e01e80634ecdd
> 

Hi Jiri, Kees,

Thank you for suggesting the patch! I have attached the (locally
tested) 4.4 and 4.9 backports of that patch with this mail. (The
mainline commit applies cleanly on 4.14).

Greg, could you please consider including them in stable 4.4, 4.9
and 4.14?

Thank you very much!

Regards,
Srivatsa
VMware Photon OS

[-- Attachment #2: 4.4-fork-unconditionally-clear-stack-on-fork.patch --]
[-- Type: text/plain, Size: 3081 bytes --]

From 7e39d8ccbb0889c03ce6dc0dee0e63d78f37d0a9 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 20 Apr 2018 14:55:31 -0700
Subject: [PATCH] fork: unconditionally clear stack on fork

commit e01e80634ecdde1dd113ac43b3adad21b47f3957 upstream.

One of the classes of kernel stack content leaks[1] is exposing the
contents of prior heap or stack contents when a new process stack is
allocated.  Normally, those stacks are not zeroed, and the old contents
remain in place.  In the face of stack content exposure flaws, those
contents can leak to userspace.

Fixing this will make the kernel no longer vulnerable to these flaws, as
the stack will be wiped each time a stack is assigned to a new process.
There's not a meaningful change in runtime performance; it almost looks
like it provides a benefit.

Performing back-to-back kernel builds before:
	Run times: 157.86 157.09 158.90 160.94 160.80
	Mean: 159.12
	Std Dev: 1.54

and after:
	Run times: 159.31 157.34 156.71 158.15 160.81
	Mean: 158.46
	Std Dev: 1.46

Instead of making this a build or runtime config, Andy Lutomirski
recommended this just be enabled by default.

[1] A noisy search for many kinds of stack content leaks can be seen here:
https://cve.mitre.org/cgi-bin/cvekey.cgi?keyword=linux+kernel+stack+leak

I did some more with perf and cycle counts on running 100,000 execs of
/bin/true.

before:
Cycles: 218858861551 218853036130 214727610969 227656844122 224980542841
Mean:  221015379122.60
Std Dev: 4662486552.47

after:
Cycles: 213868945060 213119275204 211820169456 224426673259 225489986348
Mean:  217745009865.40
Std Dev: 5935559279.99

It continues to look like it's faster, though the deviation is rather
wide, but I'm not sure what I could do that would be less noisy.  I'm
open to ideas!

Link: http://lkml.kernel.org/r/20180221021659.GA37073@beast
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Laura Abbott <labbott@redhat.com>
Cc: Rasmus Villemoes <rasmus.villemoes@prevas.dk>
Cc: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[ Srivatsa: Backported to 4.4.y ]
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Srinidhi Rao <srinidhir@vmware.com>
---
 include/linux/thread_info.h | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index ff307b5..646891f 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -55,11 +55,7 @@ extern long do_no_restart_syscall(struct restart_block *parm);
 
 #ifdef __KERNEL__
 
-#ifdef CONFIG_DEBUG_STACK_USAGE
-# define THREADINFO_GFP		(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
-#else
-# define THREADINFO_GFP		(GFP_KERNEL | __GFP_NOTRACK)
-#endif
+#define THREADINFO_GFP		(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
 
 /*
  * flag set/clear/test wrappers
-- 
2.7.4


[-- Attachment #3: 4.9-fork-unconditionally-clear-stack-on-fork.patch --]
[-- Type: text/plain, Size: 3113 bytes --]

From 7debcc6438b4a0bdc9a7b509a751350dad883328 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 20 Apr 2018 14:55:31 -0700
Subject: [PATCH] fork: unconditionally clear stack on fork

commit e01e80634ecdde1dd113ac43b3adad21b47f3957 upstream.

One of the classes of kernel stack content leaks[1] is exposing the
contents of prior heap or stack contents when a new process stack is
allocated.  Normally, those stacks are not zeroed, and the old contents
remain in place.  In the face of stack content exposure flaws, those
contents can leak to userspace.

Fixing this will make the kernel no longer vulnerable to these flaws, as
the stack will be wiped each time a stack is assigned to a new process.
There's not a meaningful change in runtime performance; it almost looks
like it provides a benefit.

Performing back-to-back kernel builds before:
	Run times: 157.86 157.09 158.90 160.94 160.80
	Mean: 159.12
	Std Dev: 1.54

and after:
	Run times: 159.31 157.34 156.71 158.15 160.81
	Mean: 158.46
	Std Dev: 1.46

Instead of making this a build or runtime config, Andy Lutomirski
recommended this just be enabled by default.

[1] A noisy search for many kinds of stack content leaks can be seen here:
https://cve.mitre.org/cgi-bin/cvekey.cgi?keyword=linux+kernel+stack+leak

I did some more with perf and cycle counts on running 100,000 execs of
/bin/true.

before:
Cycles: 218858861551 218853036130 214727610969 227656844122 224980542841
Mean:  221015379122.60
Std Dev: 4662486552.47

after:
Cycles: 213868945060 213119275204 211820169456 224426673259 225489986348
Mean:  217745009865.40
Std Dev: 5935559279.99

It continues to look like it's faster, though the deviation is rather
wide, but I'm not sure what I could do that would be less noisy.  I'm
open to ideas!

Link: http://lkml.kernel.org/r/20180221021659.GA37073@beast
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Laura Abbott <labbott@redhat.com>
Cc: Rasmus Villemoes <rasmus.villemoes@prevas.dk>
Cc: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[ Srivatsa: Backported to 4.9.y ]
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Srinidhi Rao <srinidhir@vmware.com>
---
 include/linux/thread_info.h | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 2873baf..5e64367 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -59,12 +59,7 @@ extern long do_no_restart_syscall(struct restart_block *parm);
 
 #ifdef __KERNEL__
 
-#ifdef CONFIG_DEBUG_STACK_USAGE
-# define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | \
-				 __GFP_ZERO)
-#else
-# define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT | __GFP_NOTRACK)
-#endif
+#define THREADINFO_GFP	(GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | __GFP_ZERO)
 
 /*
  * flag set/clear/test wrappers
-- 
2.7.4

Re: [RESEND] Spectre-v2 (IBPB/IBRS) and SSBD fixes for 4.4.y

[Srivatsa S. Bhat]

[-- Attachment #1: Type: text/plain, Size: 1932 bytes --]

On 8/2/18 3:22 PM, Kees Cook wrote:
> On Thu, Aug 2, 2018 at 12:22 PM, Srivatsa S. Bhat
> <srivatsa@csail.mit.edu> wrote:
>> On 7/26/18 4:09 PM, Kees Cook wrote:
>>> On Tue, Jul 24, 2018 at 3:02 PM, Jiri Kosina <jikos@kernel.org> wrote:
>>>> On Tue, 24 Jul 2018, Srivatsa S. Bhat wrote:
>>>>
>>>>> However, if you are proposing that you'd like to contribute the enhanced
>>>>> PTI/Spectre (upstream) patches from the SLES 4.4 tree to 4.4 stable, and
>>>>> have them merged instead of this patch series, then I would certainly
>>>>> welcome it!
>>>>
>>>> I'd in principle love us to push everything back to 4.4, but there are a
>>>> few reasons (*) why that's not happening shortly.
>>>>
>>>> Anyway, to point out explicitly what's really needed for those folks
>>>> running 4.4-stable and relying on PTI providing The Real Thing(TM), it's
>>>> either a 4.4-stable port of
>>>>
>>>>         http://kernel.suse.com/cgit/kernel-source/plain/patches.suse/x86-entry-64-use-a-per-cpu-trampoline-stack.patch?id=3428a77b02b1ba03e45d8fc352ec350429f57fc7
>>>>
>>>> or making THREADINFO_GFP imply __GFP_ZERO.
>>>
>>> This is true in Linus's tree now. Should be trivial to backport:
>>> https://git.kernel.org/linus/e01e80634ecdd
>>>
>>
>> Hi Jiri, Kees,
>>
>> Thank you for suggesting the patch! I have attached the (locally
>> tested) 4.4 and 4.9 backports of that patch with this mail. (The
>> mainline commit applies cleanly on 4.14).
>>
>> Greg, could you please consider including them in stable 4.4, 4.9
>> and 4.14?
> 
> I don't think your v4.9 is sufficient: it leaves the vmapped stack
> uncleared. v4.9 needs ca182551857 ("kmemleak: clear stale pointers
> from task stacks") included in the backport (really, just adding the
> memset()).
> 

Ah, I see, thank you! I have attached the updated patchset for 4.9
with this mail.

> Otherwise, yup, looks good.
> 
Thank you for reviewing the patches!
 
Regards,
Srivatsa
VMware Photon OS

[-- Attachment #2: 4.9-0001-kmemleak-clear-stale-pointers-from-task-stacks.patch --]
[-- Type: text/plain, Size: 1906 bytes --]

From edf835d8b6bac08bc5e69efb3e1cc321e2457f61 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Fri, 13 Oct 2017 15:58:22 -0700
Subject: [PATCH 1/2] kmemleak: clear stale pointers from task stacks

commit ca182551857cc2c1e6a2b7f1e72090a137a15008 upstream.

Kmemleak considers any pointers on task stacks as references.  This
patch clears newly allocated and reused vmap stacks.

Link: http://lkml.kernel.org/r/150728990124.744199.8403409836394318684.stgit@buzz
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[ Srivatsa: Backported to 4.9.y ]
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
---
 include/linux/thread_info.h | 2 +-
 kernel/fork.c               | 4 ++++
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 2873baf..cf87c16 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -59,7 +59,7 @@ extern long do_no_restart_syscall(struct restart_block *parm);
 
 #ifdef __KERNEL__
 
-#ifdef CONFIG_DEBUG_STACK_USAGE
+#if IS_ENABLED(CONFIG_DEBUG_STACK_USAGE) || IS_ENABLED(CONFIG_DEBUG_KMEMLEAK)
 # define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | \
 				 __GFP_ZERO)
 #else
diff --git a/kernel/fork.c b/kernel/fork.c
index 70e10cb..c19e6d4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -184,6 +184,10 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
 			continue;
 		this_cpu_write(cached_stacks[i], NULL);
 
+#ifdef CONFIG_DEBUG_KMEMLEAK
+		/* Clear stale pointers from reused stack. */
+		memset(s->addr, 0, THREAD_SIZE);
+#endif
 		tsk->stack_vm_area = s;
 		local_irq_enable();
 		return s->addr;
-- 
2.7.4


[-- Attachment #3: 4.9-0002-fork-unconditionally-clear-stack-on-fork.patch --]
[-- Type: text/plain, Size: 3670 bytes --]

From 5371cd0bb1e2ca8d1603845c764e1524f7e729ad Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 20 Apr 2018 14:55:31 -0700
Subject: [PATCH 2/2] fork: unconditionally clear stack on fork

commit e01e80634ecdde1dd113ac43b3adad21b47f3957 upstream.

One of the classes of kernel stack content leaks[1] is exposing the
contents of prior heap or stack contents when a new process stack is
allocated.  Normally, those stacks are not zeroed, and the old contents
remain in place.  In the face of stack content exposure flaws, those
contents can leak to userspace.

Fixing this will make the kernel no longer vulnerable to these flaws, as
the stack will be wiped each time a stack is assigned to a new process.
There's not a meaningful change in runtime performance; it almost looks
like it provides a benefit.

Performing back-to-back kernel builds before:
	Run times: 157.86 157.09 158.90 160.94 160.80
	Mean: 159.12
	Std Dev: 1.54

and after:
	Run times: 159.31 157.34 156.71 158.15 160.81
	Mean: 158.46
	Std Dev: 1.46

Instead of making this a build or runtime config, Andy Lutomirski
recommended this just be enabled by default.

[1] A noisy search for many kinds of stack content leaks can be seen here:
https://cve.mitre.org/cgi-bin/cvekey.cgi?keyword=linux+kernel+stack+leak

I did some more with perf and cycle counts on running 100,000 execs of
/bin/true.

before:
Cycles: 218858861551 218853036130 214727610969 227656844122 224980542841
Mean:  221015379122.60
Std Dev: 4662486552.47

after:
Cycles: 213868945060 213119275204 211820169456 224426673259 225489986348
Mean:  217745009865.40
Std Dev: 5935559279.99

It continues to look like it's faster, though the deviation is rather
wide, but I'm not sure what I could do that would be less noisy.  I'm
open to ideas!

Link: http://lkml.kernel.org/r/20180221021659.GA37073@beast
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Laura Abbott <labbott@redhat.com>
Cc: Rasmus Villemoes <rasmus.villemoes@prevas.dk>
Cc: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[ Srivatsa: Backported to 4.9.y ]
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Srinidhi Rao <srinidhir@vmware.com>
---
 include/linux/thread_info.h | 7 +------
 kernel/fork.c               | 3 +--
 2 files changed, 2 insertions(+), 8 deletions(-)

diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index cf87c16..5e64367 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -59,12 +59,7 @@ extern long do_no_restart_syscall(struct restart_block *parm);
 
 #ifdef __KERNEL__
 
-#if IS_ENABLED(CONFIG_DEBUG_STACK_USAGE) || IS_ENABLED(CONFIG_DEBUG_KMEMLEAK)
-# define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | \
-				 __GFP_ZERO)
-#else
-# define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT | __GFP_NOTRACK)
-#endif
+#define THREADINFO_GFP	(GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | __GFP_ZERO)
 
 /*
  * flag set/clear/test wrappers
diff --git a/kernel/fork.c b/kernel/fork.c
index c19e6d4..2c98b98 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -184,10 +184,9 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
 			continue;
 		this_cpu_write(cached_stacks[i], NULL);
 
-#ifdef CONFIG_DEBUG_KMEMLEAK
 		/* Clear stale pointers from reused stack. */
 		memset(s->addr, 0, THREAD_SIZE);
-#endif
+
 		tsk->stack_vm_area = s;
 		local_irq_enable();
 		return s->addr;
-- 
2.7.4

Re: [RESEND] Spectre-v2 (IBPB/IBRS) and SSBD fixes for 4.4.y

[Greg KH]

On Fri, Aug 03, 2018 at 04:20:31PM -0700, Srivatsa S. Bhat wrote:
> On 8/2/18 3:22 PM, Kees Cook wrote:
> > On Thu, Aug 2, 2018 at 12:22 PM, Srivatsa S. Bhat
> > <srivatsa@csail.mit.edu> wrote:
> >> On 7/26/18 4:09 PM, Kees Cook wrote:
> >>> On Tue, Jul 24, 2018 at 3:02 PM, Jiri Kosina <jikos@kernel.org> wrote:
> >>>> On Tue, 24 Jul 2018, Srivatsa S. Bhat wrote:
> >>>>
> >>>>> However, if you are proposing that you'd like to contribute the enhanced
> >>>>> PTI/Spectre (upstream) patches from the SLES 4.4 tree to 4.4 stable, and
> >>>>> have them merged instead of this patch series, then I would certainly
> >>>>> welcome it!
> >>>>
> >>>> I'd in principle love us to push everything back to 4.4, but there are a
> >>>> few reasons (*) why that's not happening shortly.
> >>>>
> >>>> Anyway, to point out explicitly what's really needed for those folks
> >>>> running 4.4-stable and relying on PTI providing The Real Thing(TM), it's
> >>>> either a 4.4-stable port of
> >>>>
> >>>>         http://kernel.suse.com/cgit/kernel-source/plain/patches.suse/x86-entry-64-use-a-per-cpu-trampoline-stack.patch?id=3428a77b02b1ba03e45d8fc352ec350429f57fc7
> >>>>
> >>>> or making THREADINFO_GFP imply __GFP_ZERO.
> >>>
> >>> This is true in Linus's tree now. Should be trivial to backport:
> >>> https://git.kernel.org/linus/e01e80634ecdd
> >>>
> >>
> >> Hi Jiri, Kees,
> >>
> >> Thank you for suggesting the patch! I have attached the (locally
> >> tested) 4.4 and 4.9 backports of that patch with this mail. (The
> >> mainline commit applies cleanly on 4.14).
> >>
> >> Greg, could you please consider including them in stable 4.4, 4.9
> >> and 4.14?
> > 
> > I don't think your v4.9 is sufficient: it leaves the vmapped stack
> > uncleared. v4.9 needs ca182551857 ("kmemleak: clear stale pointers
> > from task stacks") included in the backport (really, just adding the
> > memset()).
> > 
> 
> Ah, I see, thank you! I have attached the updated patchset for 4.9
> with this mail.
> 
> > Otherwise, yup, looks good.
> > 
> Thank you for reviewing the patches!
>  
> Regards,
> Srivatsa
> VMware Photon OS

These work for 4.9, do you also have a set for 4.4?

thanks,

greg k-h

Re: [RESEND] Spectre-v2 (IBPB/IBRS) and SSBD fixes for 4.4.y

[Srivatsa S. Bhat]

[-- Attachment #1: Type: text/plain, Size: 2649 bytes --]

On 8/7/18 6:49 AM, Greg KH wrote:
> On Fri, Aug 03, 2018 at 04:20:31PM -0700, Srivatsa S. Bhat wrote:
>> On 8/2/18 3:22 PM, Kees Cook wrote:
>>> On Thu, Aug 2, 2018 at 12:22 PM, Srivatsa S. Bhat
>>> <srivatsa@csail.mit.edu> wrote:
>>>> On 7/26/18 4:09 PM, Kees Cook wrote:
>>>>> On Tue, Jul 24, 2018 at 3:02 PM, Jiri Kosina <jikos@kernel.org> wrote:
>>>>>> On Tue, 24 Jul 2018, Srivatsa S. Bhat wrote:
>>>>>>
>>>>>>> However, if you are proposing that you'd like to contribute the enhanced
>>>>>>> PTI/Spectre (upstream) patches from the SLES 4.4 tree to 4.4 stable, and
>>>>>>> have them merged instead of this patch series, then I would certainly
>>>>>>> welcome it!
>>>>>>
>>>>>> I'd in principle love us to push everything back to 4.4, but there are a
>>>>>> few reasons (*) why that's not happening shortly.
>>>>>>
>>>>>> Anyway, to point out explicitly what's really needed for those folks
>>>>>> running 4.4-stable and relying on PTI providing The Real Thing(TM), it's
>>>>>> either a 4.4-stable port of
>>>>>>
>>>>>>         http://kernel.suse.com/cgit/kernel-source/plain/patches.suse/x86-entry-64-use-a-per-cpu-trampoline-stack.patch?id=3428a77b02b1ba03e45d8fc352ec350429f57fc7
>>>>>>
>>>>>> or making THREADINFO_GFP imply __GFP_ZERO.
>>>>>
>>>>> This is true in Linus's tree now. Should be trivial to backport:
>>>>> https://git.kernel.org/linus/e01e80634ecdd
>>>>>
>>>>
>>>> Hi Jiri, Kees,
>>>>
>>>> Thank you for suggesting the patch! I have attached the (locally
>>>> tested) 4.4 and 4.9 backports of that patch with this mail. (The
>>>> mainline commit applies cleanly on 4.14).
>>>>
>>>> Greg, could you please consider including them in stable 4.4, 4.9
>>>> and 4.14?
>>>
>>> I don't think your v4.9 is sufficient: it leaves the vmapped stack
>>> uncleared. v4.9 needs ca182551857 ("kmemleak: clear stale pointers
>>> from task stacks") included in the backport (really, just adding the
>>> memset()).
>>>
>>
>> Ah, I see, thank you! I have attached the updated patchset for 4.9
>> with this mail.
>>
>>> Otherwise, yup, looks good.
>>>
>> Thank you for reviewing the patches!
>>  
>> Regards,
>> Srivatsa
>> VMware Photon OS
> 
> These work for 4.9, do you also have a set for 4.4?
> 

Thank you for considering these patches for 4.9!

The (single) patch for 4.4 did not need any more changes, and hence is
the same as the one I attached in my previous mail. I'll attach it
again here for your reference.

Also, upstream commit e01e80634ecdde1 (fork: unconditionally clear
stack on fork) applies cleanly on 4.14 stable, so it would be great to
cherry-pick it to 4.14 stable as well.

Thank you!

Regards,
Srivatsa
VMware Photon OS

[-- Attachment #2: 4.4-fork-unconditionally-clear-stack-on-fork.patch --]
[-- Type: text/plain, Size: 3081 bytes --]

From 7e39d8ccbb0889c03ce6dc0dee0e63d78f37d0a9 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 20 Apr 2018 14:55:31 -0700
Subject: [PATCH] fork: unconditionally clear stack on fork

commit e01e80634ecdde1dd113ac43b3adad21b47f3957 upstream.

One of the classes of kernel stack content leaks[1] is exposing the
contents of prior heap or stack contents when a new process stack is
allocated.  Normally, those stacks are not zeroed, and the old contents
remain in place.  In the face of stack content exposure flaws, those
contents can leak to userspace.

Fixing this will make the kernel no longer vulnerable to these flaws, as
the stack will be wiped each time a stack is assigned to a new process.
There's not a meaningful change in runtime performance; it almost looks
like it provides a benefit.

Performing back-to-back kernel builds before:
	Run times: 157.86 157.09 158.90 160.94 160.80
	Mean: 159.12
	Std Dev: 1.54

and after:
	Run times: 159.31 157.34 156.71 158.15 160.81
	Mean: 158.46
	Std Dev: 1.46

Instead of making this a build or runtime config, Andy Lutomirski
recommended this just be enabled by default.

[1] A noisy search for many kinds of stack content leaks can be seen here:
https://cve.mitre.org/cgi-bin/cvekey.cgi?keyword=linux+kernel+stack+leak

I did some more with perf and cycle counts on running 100,000 execs of
/bin/true.

before:
Cycles: 218858861551 218853036130 214727610969 227656844122 224980542841
Mean:  221015379122.60
Std Dev: 4662486552.47

after:
Cycles: 213868945060 213119275204 211820169456 224426673259 225489986348
Mean:  217745009865.40
Std Dev: 5935559279.99

It continues to look like it's faster, though the deviation is rather
wide, but I'm not sure what I could do that would be less noisy.  I'm
open to ideas!

Link: http://lkml.kernel.org/r/20180221021659.GA37073@beast
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Laura Abbott <labbott@redhat.com>
Cc: Rasmus Villemoes <rasmus.villemoes@prevas.dk>
Cc: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[ Srivatsa: Backported to 4.4.y ]
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Srinidhi Rao <srinidhir@vmware.com>
---
 include/linux/thread_info.h | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index ff307b5..646891f 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -55,11 +55,7 @@ extern long do_no_restart_syscall(struct restart_block *parm);
 
 #ifdef __KERNEL__
 
-#ifdef CONFIG_DEBUG_STACK_USAGE
-# define THREADINFO_GFP		(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
-#else
-# define THREADINFO_GFP		(GFP_KERNEL | __GFP_NOTRACK)
-#endif
+#define THREADINFO_GFP		(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
 
 /*
  * flag set/clear/test wrappers
-- 
2.7.4

Re: [RESEND] Spectre-v2 (IBPB/IBRS) and SSBD fixes for 4.4.y

[Greg KH]

On Tue, Aug 07, 2018 at 12:08:07PM -0700, Srivatsa S. Bhat wrote:
> Also, upstream commit e01e80634ecdde1 (fork: unconditionally clear
> stack on fork) applies cleanly on 4.14 stable, so it would be great to
> cherry-pick it to 4.14 stable as well.

It is already in the 4.14.60 release, did I somehow mess up the
backport?

thanks,

greg k-h

Re: [RESEND] Spectre-v2 (IBPB/IBRS) and SSBD fixes for 4.4.y

[Srivatsa S. Bhat]

On 8/7/18 12:15 PM, Greg KH wrote:
> On Tue, Aug 07, 2018 at 12:08:07PM -0700, Srivatsa S. Bhat wrote:
>> Also, upstream commit e01e80634ecdde1 (fork: unconditionally clear
>> stack on fork) applies cleanly on 4.14 stable, so it would be great to
>> cherry-pick it to 4.14 stable as well.
> 
> It is already in the 4.14.60 release, did I somehow mess up the
> backport?
> 

Sorry, my bad! The backport in 4.14.60 looks fine. Thank you!
 
Regards,
Srivatsa
VMware Photon OS